├── DiaBLa-corpus ├── users │ ├── 22.json │ ├── 58.json │ ├── 7.json │ ├── 11.json │ ├── 14.json │ ├── 17.json │ ├── 19.json │ ├── 2.json │ ├── 20.json │ ├── 21.json │ ├── 23.json │ ├── 24.json │ ├── 25.json │ ├── 28.json │ ├── 30.json │ ├── 31.json │ ├── 33.json │ ├── 34.json │ ├── 35.json │ ├── 36.json │ ├── 40.json │ ├── 43.json │ ├── 44.json │ ├── 46.json │ ├── 53.json │ ├── 55.json │ ├── 56.json │ ├── 57.json │ ├── 6.json │ ├── 61.json │ ├── 63.json │ ├── 67.json │ ├── 68.json │ ├── 69.json │ ├── 72.json │ ├── 73.json │ ├── 8.json │ ├── 9.json │ ├── 10.json │ ├── 12.json │ ├── 13.json │ ├── 15.json │ ├── 18.json │ ├── 26.json │ ├── 29.json │ ├── 3.json │ ├── 39.json │ ├── 41.json │ ├── 45.json │ ├── 47.json │ ├── 48.json │ ├── 49.json │ ├── 50.json │ ├── 51.json │ ├── 52.json │ ├── 54.json │ ├── 59.json │ ├── 60.json │ ├── 62.json │ ├── 70.json │ ├── 74.json │ ├── 75.json │ ├── 76.json │ ├── 37.json │ ├── 38.json │ ├── 4.json │ ├── 42.json │ ├── 5.json │ ├── 1.json │ ├── 27.json │ ├── 32.json │ ├── 65.json │ ├── 66.json │ ├── 77.json │ ├── 16.json │ ├── 64.json │ └── 71.json ├── meta_info │ ├── anonymisation.txt │ └── scenarios.txt ├── dialogues │ ├── 2018-05-17T10-57-19.461882_french_english_58_59.json │ ├── 2018-05-04T19-18-57.178971_french_english_16_3.json │ ├── 2018-05-17T13-10-59.820782_french_english_58_10.json │ └── 2018-05-14T13-21-20.795702_french_english_50_3.json └── all-users.json ├── scripts ├── filter-sents-for-eval.sh └── extract-raw-corpus.py ├── README.md └── LICENSE /DiaBLa-corpus/users/22.json: -------------------------------------------------------------------------------- 1 | { 2 | "idnum": 22, 3 | "french_ability": "native", 4 | "age": "25-34", 5 | "gender": "male", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "creation_date": "2018-04-29T11:55:09.656535", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/58.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 58, 4 | "gender": "male", 5 | "creation_date": "2018-05-17T10:46:28.639646", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/7.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "male", 3 | "otherlangs": "", 4 | "english_ability": "good", 5 | "idnum": 7, 6 | "french_ability": "native", 7 | "age": "25-34", 8 | "creation_date": "2018-04-27T10:49:05.761531", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/11.json: -------------------------------------------------------------------------------- 1 | { 2 | "otherlangs": "", 3 | "gender": "female", 4 | "age": "25-34", 5 | "creation_date": "2018-04-29T12:47:58.686184", 6 | "idnum": 11, 7 | "english_ability": "native", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/14.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "good", 3 | "otherlangs": "", 4 | "age": "18-24", 5 | "idnum": 14, 6 | "french_ability": "native", 7 | "creation_date": "2018-04-26T13:27:11.416655", 8 | "gender": "female", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/17.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "", 4 | "age": "55-64", 5 | "idnum": 17, 6 | "creation_date": "2018-04-27T16:57:00.520643", 7 | "french_ability": "poor", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/19.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "age": "45-54", 4 | "gender": "female", 5 | "english_ability": "poor", 6 | "otherlangs": "", 7 | "creation_date": "2018-04-30T17:03:23.475142", 8 | "idnum": 19, 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/2.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "", 4 | "age": "55-64", 5 | "idnum": 2, 6 | "french_ability": "medium", 7 | "creation_date": "2018-04-25T09:34:50.357566", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/20.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "18-24", 3 | "idnum": 20, 4 | "gender": "female", 5 | "creation_date": "2018-05-01T11:15:03.938877", 6 | "english_ability": "native", 7 | "otherlangs": "", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/21.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "45-54", 3 | "gender": "male", 4 | "english_ability": "native", 5 | "idnum": 21, 6 | "otherlangs": "", 7 | "creation_date": "2018-05-01T12:52:36.913957", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/23.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 23, 4 | "gender": "male", 5 | "creation_date": "2018-04-29T12:30:25.985724", 6 | "english_ability": "native", 7 | "otherlangs": "", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/24.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "female", 3 | "english_ability": "native", 4 | "otherlangs": "", 5 | "age": "55-64", 6 | "idnum": 24, 7 | "creation_date": "2018-04-30T11:12:05.976575", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/25.json: -------------------------------------------------------------------------------- 1 | { 2 | "idnum": 25, 3 | "french_ability": "native", 4 | "age": "25-34", 5 | "gender": "male", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "creation_date": "2018-05-02T19:30:10.455938", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/28.json: -------------------------------------------------------------------------------- 1 | { 2 | "idnum": 28, 3 | "french_ability": "poor", 4 | "age": "25-34", 5 | "gender": "male", 6 | "english_ability": "native", 7 | "otherlangs": "", 8 | "creation_date": "2018-04-30T16:38:02.633151", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/30.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "45-54", 3 | "idnum": 30, 4 | "gender": "female", 5 | "creation_date": "2018-05-03T12:00:44.072467", 6 | "english_ability": "medium", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/31.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "55-64", 3 | "gender": "male", 4 | "idnum": 31, 5 | "otherlangs": "none", 6 | "creation_date": "2018-05-01T15:05:04.396938", 7 | "french_ability": "poor", 8 | "english_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/33.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "65-74", 3 | "gender": "male", 4 | "idnum": 33, 5 | "otherlangs": "", 6 | "creation_date": "2018-05-03T13:15:51.206957", 7 | "french_ability": "poor", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/34.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "45-54", 3 | "idnum": 34, 4 | "gender": "male", 5 | "creation_date": "2018-05-04T16:09:58.277387", 6 | "english_ability": "native", 7 | "otherlangs": "", 8 | "french_ability": "none", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/35.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "gender": "male", 4 | "english_ability": "medium", 5 | "otherlangs": "", 6 | "creation_date": "2018-05-04T19:19:49.702669", 7 | "idnum": 35, 8 | "age": "35-44", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/36.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "55-64", 3 | "idnum": 36, 4 | "gender": "female", 5 | "creation_date": "2018-05-05T12:21:51.443415", 6 | "english_ability": "native", 7 | "otherlangs": "", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/40.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "35-44", 3 | "gender": "female", 4 | "idnum": 40, 5 | "otherlangs": "", 6 | "creation_date": "2018-05-08T18:42:39.567200", 7 | "french_ability": "native", 8 | "english_ability": "good", 9 | "worked_in_research": true, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/43.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "65-74", 3 | "idnum": 43, 4 | "gender": "male", 5 | "creation_date": "2018-05-08T18:52:41.506093", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/44.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "gender": "male", 4 | "idnum": 44, 5 | "otherlangs": "", 6 | "creation_date": "2018-05-09T18:22:11.735377", 7 | "french_ability": "medium", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/46.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "gender": "male", 4 | "otherlangs": "", 5 | "idnum": 46, 6 | "creation_date": "2018-05-01T21:40:54.354017", 7 | "english_ability": "good", 8 | "age": "35-44", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/53.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "none", 3 | "gender": "female", 4 | "otherlangs": "", 5 | "idnum": 53, 6 | "creation_date": "2018-05-14T17:45:02.506705", 7 | "english_ability": "native", 8 | "age": "55-64", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/55.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "good", 3 | "otherlangs": "", 4 | "age": "25-34", 5 | "idnum": 55, 6 | "creation_date": "2018-05-15T18:09:16.668712", 7 | "french_ability": "native", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/56.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "55-64", 3 | "idnum": 56, 4 | "gender": "female", 5 | "creation_date": "2018-05-15T18:58:26.117939", 6 | "english_ability": "native", 7 | "otherlangs": "", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/57.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 57, 4 | "gender": "male", 5 | "creation_date": "2018-05-04T12:43:55.705713", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/6.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "", 4 | "age": "55-64", 5 | "idnum": 6, 6 | "creation_date": "2018-04-27T09:05:01.484342", 7 | "french_ability": "poor", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/61.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "45-54", 3 | "idnum": 61, 4 | "gender": "male", 5 | "creation_date": "2018-05-17T11:28:51.158690", 6 | "english_ability": "good", 7 | "otherlangs": "arabe", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/63.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 63, 4 | "gender": "male", 5 | "creation_date": "2018-05-17T10:00:08.411214", 6 | "english_ability": "native", 7 | "otherlangs": "dutch", 8 | "french_ability": "none", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/67.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 67, 4 | "gender": "female", 5 | "creation_date": "2018-05-17T18:34:28.910854", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/68.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 68, 4 | "gender": "male", 5 | "creation_date": "2018-05-18T08:17:32.624100", 6 | "english_ability": "good", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/69.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "35-44", 3 | "idnum": 69, 4 | "gender": "male", 5 | "creation_date": "2018-05-16T15:27:48.255858", 6 | "english_ability": "medium", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/72.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "male", 3 | "english_ability": "medium", 4 | "otherlangs": "", 5 | "age": "25-34", 6 | "idnum": 72, 7 | "creation_date": "2018-05-18T16:05:45.910456", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/73.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "male", 3 | "english_ability": "good", 4 | "otherlangs": "", 5 | "age": "25-34", 6 | "idnum": 73, 7 | "creation_date": "2018-05-18T16:54:38.039162", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/8.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "female", 3 | "otherlangs": "", 4 | "english_ability": "good", 5 | "idnum": 8, 6 | "french_ability": "native", 7 | "age": "25-34", 8 | "creation_date": "2018-04-27T13:26:32.153820", 9 | "worked_in_research": true, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/9.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "poor", 3 | "gender": "female", 4 | "idnum": 9, 5 | "english_ability": "native", 6 | "age": "25-34", 7 | "creation_date": "2018-04-28T07:36:20.122686", 8 | "otherlangs": "", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/10.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "none", 4 | "age": "55-64", 5 | "idnum": 10, 6 | "creation_date": "2018-04-27T13:12:00.631492", 7 | "french_ability": "poor", 8 | "gender": "male", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/12.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "english_ability": "good", 4 | "otherlangs": "allemand", 5 | "gender": "male", 6 | "age": "35-44", 7 | "idnum": 12, 8 | "creation_date": "2018-04-27T21:50:58.298417", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/13.json: -------------------------------------------------------------------------------- 1 | { 2 | "otherlangs": "dutch", 3 | "gender": "female", 4 | "age": "25-34", 5 | "creation_date": "2018-04-29T15:25:19.699471", 6 | "idnum": 13, 7 | "english_ability": "good", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/15.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "good", 3 | "otherlangs": "spanish", 4 | "age": "25-34", 5 | "idnum": 15, 6 | "creation_date": "2018-04-30T09:23:28.281142", 7 | "french_ability": "native", 8 | "gender": "male", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/18.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "good", 3 | "gender": "male", 4 | "english_ability": "native", 5 | "otherlangs": "spanish", 6 | "creation_date": "2018-04-27T20:09:24.216476", 7 | "idnum": 18, 8 | "age": "55-64", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/26.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "gender": "female", 4 | "otherlangs": "", 5 | "english_ability": "medium", 6 | "creation_date": "2018-05-02T19:40:23.480969", 7 | "idnum": 26, 8 | "age": "25-34", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/29.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "65-74", 3 | "gender": "male", 4 | "idnum": 29, 5 | "otherlangs": "none", 6 | "creation_date": "2018-05-01T06:34:59.055115", 7 | "french_ability": "poor", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/3.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "", 4 | "age": "25-34", 5 | "idnum": 3, 6 | "creation_date": "2018-04-25T09:46:50.458906", 7 | "french_ability": "near-native", 8 | "gender": "female", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/39.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "55-64", 3 | "gender": "female", 4 | "idnum": 39, 5 | "otherlangs": "", 6 | "creation_date": "2018-05-08T12:44:39.770276", 7 | "french_ability": "native", 8 | "english_ability": "medium", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/41.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "55-64", 3 | "gender": "male", 4 | "idnum": 41, 5 | "otherlangs": "arabic", 6 | "creation_date": "2018-05-08T19:06:59.794483", 7 | "french_ability": "medium", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/45.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "female", 3 | "english_ability": "good", 4 | "otherlangs": "none", 5 | "age": "65-74", 6 | "idnum": 45, 7 | "creation_date": "2018-05-09T19:59:53.841263", 8 | "french_ability": "none", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/47.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "gender": "female", 4 | "otherlangs": "", 5 | "idnum": 47, 6 | "creation_date": "2018-05-11T19:09:10.200728", 7 | "english_ability": "medium", 8 | "age": "35-44", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/48.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "medium", 3 | "gender": "female", 4 | "english_ability": "native", 5 | "otherlangs": "", 6 | "creation_date": "2018-05-04T16:55:29.021776", 7 | "idnum": 48, 8 | "age": "55-64", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/49.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "near-native", 3 | "otherlangs": "", 4 | "age": "65-74", 5 | "idnum": 49, 6 | "gender": "male", 7 | "creation_date": "2018-05-12T19:11:54.301318", 8 | "french_ability": "poor", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/50.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "native", 3 | "gender": "male", 4 | "english_ability": "good", 5 | "otherlangs": "allemand", 6 | "creation_date": "2018-05-14T13:20:08.369903", 7 | "idnum": 50, 8 | "age": "45-54", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/51.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "poor", 3 | "gender": "female", 4 | "english_ability": "native", 5 | "otherlangs": "none", 6 | "creation_date": "2018-05-14T18:37:04.825042", 7 | "idnum": 51, 8 | "age": "55-64", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/52.json: -------------------------------------------------------------------------------- 1 | { 2 | "french_ability": "poor", 3 | "gender": "female", 4 | "english_ability": "native", 5 | "otherlangs": "none", 6 | "creation_date": "2018-05-14T18:38:29.372010", 7 | "idnum": 52, 8 | "age": "45-54", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/54.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "25-34", 3 | "idnum": 54, 4 | "gender": "female", 5 | "creation_date": "2018-05-15T12:59:42.603597", 6 | "english_ability": "medium", 7 | "otherlangs": "", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/59.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "35-44", 3 | "idnum": 59, 4 | "gender": "female", 5 | "creation_date": "2018-05-17T10:11:46.659337", 6 | "english_ability": "native", 7 | "otherlangs": "german", 8 | "french_ability": "medium", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/60.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "35-44", 3 | "idnum": 60, 4 | "gender": "male", 5 | "creation_date": "2018-05-17T11:13:36.994382", 6 | "english_ability": "good", 7 | "otherlangs": "german", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/62.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "medium", 3 | "otherlangs": "", 4 | "age": "25-34", 5 | "idnum": 62, 6 | "creation_date": "2018-05-17T10:07:59.208971", 7 | "french_ability": "native", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/70.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "male", 3 | "english_ability": "good", 4 | "otherlangs": "spanish", 5 | "age": "45-54", 6 | "idnum": 70, 7 | "creation_date": "2018-05-18T13:24:01.586193", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/74.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "", 4 | "age": "18-24", 5 | "idnum": 74, 6 | "creation_date": "2018-05-08T18:59:02.753243", 7 | "french_ability": "native", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/75.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "female", 3 | "english_ability": "native", 4 | "otherlangs": "", 5 | "age": "55-64", 6 | "idnum": 75, 7 | "creation_date": "2018-05-21T18:08:52.358225", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/76.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "good", 3 | "otherlangs": "german", 4 | "age": "25-34", 5 | "idnum": 76, 6 | "creation_date": "2018-05-15T07:32:29.245082", 7 | "french_ability": "native", 8 | "gender": "male", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/37.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "65-74", 3 | "gender": "female", 4 | "idnum": 37, 5 | "otherlangs": "", 6 | "creation_date": "2018-05-07T13:35:50.726778", 7 | "french_ability": "near-native", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/38.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "65-74", 3 | "gender": "female", 4 | "idnum": 38, 5 | "otherlangs": "german", 6 | "creation_date": "2018-05-07T19:12:09.913326", 7 | "french_ability": "medium", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/4.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "35-44", 3 | "idnum": 4, 4 | "gender": "female", 5 | "creation_date": "2018-04-26T20:09:50.034718", 6 | "english_ability": "near-native", 7 | "otherlangs": "german", 8 | "french_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/42.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "55-64", 3 | "gender": "female", 4 | "idnum": 42, 5 | "otherlangs": "spanish", 6 | "creation_date": "2018-05-08T18:34:17.964134", 7 | "french_ability": "medium", 8 | "english_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/5.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "male", 3 | "idnum": 5, 4 | "age": "55-64", 5 | "creation_date": "2018-04-26T20:43:07.578120", 6 | "french_ability": "good", 7 | "otherlangs": "german, estonian", 8 | "english_ability": "native", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/1.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "near-native", 3 | "otherlangs": "german, slovak", 4 | "age": "35-44", 5 | "idnum": 1, 6 | "creation_date": "2018-04-24T13:34:36.142332", 7 | "french_ability": "native", 8 | "gender": "male", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/27.json: -------------------------------------------------------------------------------- 1 | { 2 | "idnum": 27, 3 | "english_ability": "good", 4 | "age": "25-34", 5 | "gender": "male", 6 | "french_ability": "native", 7 | "otherlangs": "german/allemand", 8 | "creation_date": "2018-04-27T21:56:16.066322", 9 | "worked_in_research": false, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/32.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "45-54", 3 | "gender": "male", 4 | "idnum": 32, 5 | "otherlangs": "spanish, italian", 6 | "creation_date": "2018-05-03T13:54:36.656129", 7 | "french_ability": "native", 8 | "english_ability": "good", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/65.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "spanish", 4 | "age": "25-34", 5 | "idnum": 65, 6 | "creation_date": "2018-05-17T18:58:33.952804", 7 | "french_ability": "near-native", 8 | "gender": "male", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/66.json: -------------------------------------------------------------------------------- 1 | { 2 | "age": "18-24", 3 | "idnum": 66, 4 | "gender": "female", 5 | "creation_date": "2018-05-14T20:13:45.174188", 6 | "english_ability": "near-native", 7 | "otherlangs": "german", 8 | "french_ability": "native", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/77.json: -------------------------------------------------------------------------------- 1 | { 2 | "gender": "female", 3 | "english_ability": "native", 4 | "otherlangs": "spanish, afrikaans", 5 | "age": "35-44", 6 | "idnum": 77, 7 | "creation_date": "2018-05-21T20:46:24.095121", 8 | "french_ability": "none", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/16.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "poor", 3 | "otherlangs": "portugais (br\u00e9sil)", 4 | "age": "65-74", 5 | "idnum": 16, 6 | "creation_date": "2018-04-30T10:10:01.284911", 7 | "french_ability": "native", 8 | "gender": "male", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/users/64.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "near-native", 3 | "otherlangs": "russian, spanish", 4 | "age": "25-34", 5 | "idnum": 64, 6 | "creation_date": "2018-05-17T17:15:07.264806", 7 | "french_ability": "native", 8 | "gender": "female", 9 | "worked_in_research": false, 10 | "worked_in_NLP": false, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /scripts/filter-sents-for-eval.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | [ "$#" -ne 2 ] && echo "USAGE: $0 " && exit 4 | 5 | candidate=$1 # candidate translation file 6 | filter=$2 # diabla.en2fr.eval-filter or diabla.fr2en.eval-filter 7 | 8 | # filter out these lines containing _IGNORE_FOR_EVAL_ 9 | paste $filter $candidate | grep -v '_IGNORE_FOR_EVAL_' | perl -pe 's/^\t//g' 10 | -------------------------------------------------------------------------------- /DiaBLa-corpus/users/71.json: -------------------------------------------------------------------------------- 1 | { 2 | "english_ability": "native", 3 | "otherlangs": "spanish, catalan, norwegian, russian, (portuguese, swedish)", 4 | "age": "25-34", 5 | "idnum": 71, 6 | "creation_date": "2018-05-17T12:41:23.875835", 7 | "french_ability": "medium", 8 | "gender": "male", 9 | "worked_in_research": true, 10 | "worked_in_NLP": true, 11 | "agreed_to_terms_and_conditions": true 12 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/meta_info/anonymisation.txt: -------------------------------------------------------------------------------- 1 | 2018-05-02T20-44-33.029998_french_english_22_24.json 2 | Replace with Maria in 0 3 | 4 | 2018-05-04T16-26-41.455660_french_english_4_34.json 5 | Replace with Julie in 1 6 | 7 | 2018-05-07T13-50-08.661870_french_english_1_37.json 8 | Replace with Arthur in 100 9 | 10 | 2018-05-07T14-16-18.332546_french_english_16_3.json 11 | Replace with Nina in verbatim_quality 12 | 13 | 2018-05-08T19-26-56.187389_french_english_43_24.json 14 | Replace with Sandra in 31 15 | 16 | 2018-05-09T18-27-37.658753_french_english_1_44.json 17 | Replace with Tristan in 49 18 | 19 | 2018-05-14T13-21-20.795702_french_english_50_3.json 20 | Replace with Caroline in 0 21 | 22 | 2018-05-14T19-29-22.875336_french_english_35_53.json 23 | Replace with Ali in 0 24 | Replace with Michelle in 3 25 | 26 | 2018-05-17T11-13-55.950622_french_english_60_59.json 27 | Replace with Sami in 0 28 | 29 | 2018-05-20T19-01-50.945289_french_english_55_45.json 30 | Replace with Alice in 2 31 | 32 | 2018-05-20T19-26-10.766239_french_english_55_17.json 33 | Replace with Emma in 0 34 | 35 | 2018-05-20T19-45-38.611553_french_english_64_17.json 36 | Replace with Louise in 0 37 | 38 | 2018-05-21T18-59-31.070231_french_english_72_17.json 39 | Replace with Sandra in 0 40 | -------------------------------------------------------------------------------- /DiaBLa-corpus/meta_info/scenarios.txt: -------------------------------------------------------------------------------- 1 | List of scenarios used and the roles for each of the participants 2 | 3 | 1. 4 | You are both lost in a forest. 5 | Vous êtes tous les deux perdus dans une forêt 6 | Role 1: N/A 7 | Role 2: N/A 8 | 9 | 2. 10 | You are chefs preparing a meal. 11 | Vous êtes deux cuisiners/cuisinières en train de préparer un repas. 12 | Role 1: 13 | You are the head chef and you are talking to your subordinate. 14 | Vous êtes le ou la chef(fe) et vous discutez avec votre chef(fe) adjoint. 15 | Role 2: 16 | You are the subordinate chef and you are talking to the head chef. 17 | Vous êtes le ou la chef(fe) adjoint(e) et vous discutez avec le/la chef(fe). 18 | 19 | 3. 20 | You are in a classroom. 21 | Vous êtes dans une salle de classe. 22 | Role 1: 23 | You are the teacher and you are talking to a student. 24 | Vous êtes le ou la professeur(e) et vous discutez avec un(e) élève(e) ou étudiant(e). 25 | Role 2: 26 | You are the student and you are talking to your teacher. 27 | Vous êtes un(e) élève(e) ou étudiant(e) et vous discutez avec votre professeur(e). 28 | 29 | 4. 30 | You are feeding the ducks by the pond. 31 | Vous nourrissez les canards au bord d'un étang. 32 | Role 1: N/A 33 | Role 2: N/A 34 | 35 | 5. 36 | You are both organising a party. 37 | Vous organisez une fête. 38 | Role 1: 39 | It's your party. 40 | C'est votre anniversaire 41 | Role 2: 42 | It's their party. 43 | C'est l'anniversaire de la personne avec qui vous discutez. 44 | 45 | 6. 46 | You are both stuck in a lift at work. 47 | Vous êtes tous les deux bloqué(e)s dans un ascenseur au travail. 48 | Role 1: 49 | You are an employee and you are with your boss. 50 | Vous êtes un(e) employé(e) et vous êtes avec votre patron(ne). 51 | Role 2: 52 | You are the boss and are with an employee. 53 | Vous êtes le ou la patron(ne) et vous êtes avec un(e) employé(e). 54 | 55 | 7. 56 | You are in a retirement home. 57 | Vous êtes dans une maison de retraite. 58 | Role 1: 59 | You are visiting and talking to an old friend. 60 | Vous rendez visite et discutez avec un(e) vieil(le) ami(e). 61 | Role 2: 62 | You are a resident and you are talking with an old friend who is visiting you. 63 | Vous êtes un résident(e). Vous discutez avec un vieil ami qui est venu vous rendre visite. 64 | 65 | 8. 66 | You are in a bar. 67 | Vous êtes dans un bar. 68 | Role 1: 69 | You are the bartender and talking to a customer. 70 | Vous êtes barman/barmaid et vous parlez à un(e) client(e). 71 | Role 2: 72 | You are a customer and are talking to the bartender. 73 | Vous êtes un(e) client(e) et vous parlez au barman/à la barmaid. 74 | 75 | 9. 76 | You are in an aeroplane. 77 | Vous êtes dans un avion. 78 | Role 1: 79 | You are scared and are speaking to the person sitting next to you. 80 | Vous avez peur de l'avion et parlez à la personne à côté de vous. 81 | Role 2: 82 | You are speaking to the person next to you, who is scared. 83 | Vous parlez à la personne à côté de vous, qui a peur de l'avion. 84 | 85 | 10. 86 | You are at home in the evening. 87 | Vous êtes à la maison le soir. 88 | Role 1: 89 | You are telling your spouse about the awful day you had. 90 | Vous racontez à votre partenaire la journée difficile que vous venez de passer. 91 | Role 2: 92 | You are listening to your spouse telling you about the awful day they had. 93 | Vous écoutez votre partenaire qui vous raconte la journée difficile qu'il/elle vient de passer. 94 | 95 | 11. 96 | You are in a psychiatrist's consulting room. 97 | Vous êtes dans le cabinet d'un psychiatre. 98 | Role 1: 99 | You are the psychiatrist and are with your patient. 100 | Vous êtes le psychiatre et parlez avec l'un(e) de vos patients. 101 | Role 2: 102 | You are a patient and you are talking to your psychiatrist. 103 | Vous êtes le ou la patient(e) et parlez avec votre psychiatre. 104 | 105 | 12. 106 | You are on holiday by the pool. 107 | Vous êtes en vacances à côté de la piscine. 108 | Role 1: 109 | You are trying to relax and the other person wants to do something else. 110 | Vous essayez de vous reposer et l'autre personne veut faire autre chose. 111 | Role 2: 112 | You want to do something else and the other person is trying to relax. 113 | Vous voulez faire autre chose et l'autre personne essaie de se reposer. 114 | -------------------------------------------------------------------------------- /scripts/extract-raw-corpus.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python 2 | import os, json, re 3 | 4 | def get_users_from_filename(filename): 5 | usermatch = re.match('.*?_([^_]+)_([^_]+)_(\d+)_(\d+).json', filename) 6 | lang1 = usermatch.group(1) 7 | lang2 = usermatch.group(2) 8 | user1 = usermatch.group(3) 9 | user2 = usermatch.group(4) 10 | return lang1, lang2, user1, user2 11 | 12 | 13 | def extract_file(dialogue_file, user_folder, 14 | en2fr_orig, en2fr_ref, en2fr_filter, 15 | fr2en_orig, fr2en_ref, fr2en_filter, info): 16 | 17 | dialogue = json.load(open(dialogue_file)) 18 | lang1, lang2, user1, user2 = get_users_from_filename(dialogue_file) 19 | 20 | fr_user = user1 if lang1 =='french' else user2 21 | en_user = user2 if lang1 =='french' else user1 22 | 23 | 24 | for utt_num in dialogue['utterances']: 25 | utt = dialogue['utterances'][utt_num] 26 | 27 | lang = utt['language'] 28 | text = utt['original_text'] 29 | mt = utt['postprocessed_text'] 30 | ref = utt['reference_translation'] 31 | norm = utt['normalised_version'] 32 | user = fr_user if lang == 'french' else en_user 33 | 34 | write_time = utt['composition_time'] 35 | preproc_begin = utt['preprocessing_begin'] 36 | preproc_end = utt['preprocessing_end'] 37 | translation_begin = utt['translation_begin'] 38 | translation_end = utt['translation_end'] 39 | sent_time = utt['sent_time'] 40 | 41 | #print(utt) 42 | #input() 43 | # write text to files. 44 | # _orig files contain all sentences as seen by the speaker 45 | # of the source langauge 46 | # _ref files contain all reference translations. If the source 47 | # is a machine translation, then ref line prefixed by 'IGNORE' 48 | # for evaluation purposes 49 | info_text = '\t'.join([lang, user, norm if norm != '' else 'None', 50 | write_time, sent_time, 51 | dialogue_file.split('/')[-1]]) + '\n' 52 | info.write(info_text) 53 | 54 | if lang == 'english': 55 | en2fr_orig.write(text + '\n') 56 | en2fr_ref.write(ref + '\n') 57 | fr2en_orig.write(mt + '\n') 58 | fr2en_filter.write('_IGNORE_FOR_EVAL_\n') 59 | 60 | elif lang == 'french': 61 | fr2en_orig.write(text + '\n') 62 | fr2en_ref.write(ref + '\n') 63 | en2fr_orig.write(mt + '\n') 64 | en2fr_filter.write('_IGNORE_FOR_EVAL_\n') 65 | 66 | else: 67 | print('There has been an error. ' + lang + ' is not a recognised language.') 68 | exit() 69 | 70 | 71 | def extract_all(dialogue_folder, user_folder, output_folder): 72 | 73 | # open outputs files 74 | en2fr_orig = open(output_folder + '/diabla.en2fr.orig', 'w') 75 | en2fr_ref = open(output_folder + '/diabla.en2fr.ref', 'w') 76 | en2fr_filter = open(output_folder + '/diabla.en2fr.eval-filter', 'w') 77 | fr2en_orig = open(output_folder + '/diabla.fr2en.orig', 'w') 78 | fr2en_ref = open(output_folder + '/diabla.fr2en.ref', 'w') 79 | fr2en_filter = open(output_folder + '/diabla.fr2en.eval-filter', 'w') 80 | info = open(output_folder + '/diabla.info', 'w') 81 | 82 | # for each dialogue file, extract text and write to files 83 | for dialogue_file in os.listdir(dialogue_folder): 84 | if '.json' not in dialogue_file: 85 | continue 86 | extract_file(dialogue_folder + '/' + dialogue_file, user_folder, 87 | en2fr_orig, en2fr_ref, en2fr_filter, 88 | fr2en_orig, fr2en_ref, fr2en_filter, info) 89 | 90 | # close all files 91 | en2fr_orig.close(), en2fr_ref.close(), en2fr_filter.close() 92 | fr2en_orig.close(), fr2en_ref.close(), fr2en_filter.close(), info.close() 93 | 94 | 95 | if __name__ == '__main__': 96 | 97 | import argparse 98 | parser = argparse.ArgumentParser() 99 | parser.add_argument('dialogue_folder') 100 | parser.add_argument('user_folder') 101 | parser.add_argument('output_folder') 102 | args = parser.parse_args() 103 | 104 | extract_all(args.dialogue_folder, args.user_folder, args.output_folder) 105 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # DiaBLa English-French MT dialogue dataset 2 | (Dialogue BiLingue "Bilingual Dialogue") 3 | 4 | English-French dataset for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. 5 | 6 | The test set contains 5,700+ sentences from 144 spontaneous, written dialogues between English and French speakers. The dialogues are mediated by one of two neural MT systems (a baseline RNN and a lightly contextual RNN model that uses the previous sentence). Each dialogue is associated with one of twelve varied scenarios, which are listed in `meta_info/scenarios.txt`. In addition, the participants evaluated in real time the quality of the MT systems from a monolingual point of view. Once collected, the dialogues were anonymised, and manually normalised versions of sentences were produced where necessary. Importantly, reference translations were produced for all sentences. 7 | 8 | Dialogue annotations: 9 | * fine-grained __sentence-level judgments of MT quality__, produced by the dialogue participants themselves 10 | * manually produced __reference translations__ 11 | * manually __normalised versions__ of source sentences 12 | 13 | :point_right: 14 | [Visit the website here](https://rbawden.github.io/diabla/index.html) 15 | 16 | ## Use as a test set 17 | 18 | Raw source and reference files in `DiaBLa-corpus/raw-corpus`: 19 | 20 | - Source files: `diabla.en2fr_orig` and `diabla.fr2en_orig`. 21 | - Reference files: `diabla.en2fr_ref` and `diabla.fr2en_ref`. 22 | - Info file: `diabla.info` 23 | 24 | Each source file contains the entire dialogue, from the point of view of the speaker of the source language (containing their own original sentences and the machine translated versions of the other speaker's utterances). This is important for contextual translation - to have access to all context present when the source utterances were produced. 25 | 26 | The reference files contain only those sentences that should be evaluated (i.e. the sentences that were originally in the source language). Once you have translated the entire source file, filter your translations as follows: 27 | 28 | `bash scripts/filter-sents-for-eval.sh DiaBLa-corpus/raw-corpus/diabla.{en2fr,fr2en}.eval-filter > OUT` 29 | 30 | Then evaluate the filtered sentences against the reference translations using your favourite metric. 31 | 32 | 33 | ## Citation 34 | 35 | If you use this corpus, please cite: 36 | 37 | ``` 38 | @article{bawden_DiaBLa:-A-Corpus-of_2021, 39 | author = {Bawden, Rachel and Bilinski, Eric and Lavergne, Thomas and Rosset, Sophie}, 40 | doi = {10.1007/s10579-020-09514-4}, 41 | title = {DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation}, 42 | year = {2021}, 43 | journal = {Language Resources and Evaluation}, 44 | publisher = {Springer Verlag}, 45 | volume = {55}, 46 | pages = {635--660}, 47 | url = {https://hal.inria.fr/hal-03021633}, 48 | pdf = {https://hal.inria.fr/hal-03021633/file/diabla-lre-personal-formatting.pdf}, 49 | } 50 | ``` 51 | 52 | ## Licence 53 | 54 | The dataset is distributed under a CC BY-SA 4.0 licence. 55 | 56 | ## Structure and content 57 | 58 | ### .json formatted corpus (containing all annotations) 59 | 60 | The corpus also exists in `.json` format, containing all annotations and information. All dialogue files are found `dialogues/` and information for each user is found in `users/`. 61 | 62 | Each dialogue file has the following dialogue-level information: 63 | ``` 64 | "start_time": , 65 | "scenario": [ 66 | [SCENARIO DESCRIPTION (IN ENGLISH), SCENARIO DESCRIPTION (IN FRENCH)], 67 | [ROLE 1 (IN ENGLISH), ROLE 2 (IN FRENCH)], 68 | [ROLE 2 (IN ENGLISH), ROLE 2 (IN FRENCH)] 69 | ], 70 | "user1": { 71 | "idnum": , 72 | "gender": "male/female", 73 | "age": "18-24|25-34|35-44|55-64|65-74", 74 | "turn_number": "1|2", 75 | "role": [TEXT DESCRIPTION OF ROLE (IN ENGLISH), TEXT DESCRIPTION OF ROLE (IN FRENCH)], 76 | "lang": "french or "english" 77 | } 78 | "user2": { 79 | "turn_number": "1|2", 80 | "role": [TEXT DESCRIPTION OF ROLE (IN ENGLISH), TEXT DESCRIPTION OF ROLE (IN FRENCH)], 81 | "lang": "french or "english" 82 | } 83 | "translation_model": "baseline" or "contextual", 84 | "utterances": { 85 | "0": {...}, 86 | "1": {...}, 87 | ... 88 | } 89 | ``` 90 | 91 | Each utterance in the dialogue (ids start at 0) is structured as followed: 92 | 93 | ``` 94 | id : { 95 | "language": "english/french", 96 | "original_text": , 97 | "normalised_version": , 98 | "preprocessed_text": , 99 | "translated_text": , 100 | "postprocessed_text": , 101 | "reference_translation": , 102 | "composition_time": , 103 | "preprocessing_begin": , 104 | "preprocessing_end": , 105 | "translation_begin": , 106 | "translation_end": , 107 | "postprocessing_begin": , 108 | "postprocessing_end": , 109 | "sent_time": TRANSLATION SENT, 110 | "eval": { 111 | "judgment": "poor/medium/perfect", 112 | "judgment history": [ 113 | ["poor/medium/perfect", ], [...] 114 | ] 115 | "verbatim": , 116 | "verbatim_history": [ 117 | [, ], [...] 118 | ], 119 | "problems": ["word choice", "grammaticality", "coherence", "style"], # list of problems present (if any) 120 | "problem_history": [ 121 | [, , true/false], [...] 122 | ] 123 | 124 | } 125 | ``` 126 | 127 | User files are structured as follows: 128 | 129 | ``` 130 | { 131 | "idnum": 1, 132 | "age": "18-24|25-34|35-44|55-64|65-74", 133 | "gender": "male|female", 134 | "english_ability": "poor|medium|good|near-native|native", 135 | "french_ability": "poor|medium|good|near-native|native", 136 | "otherlangs": , 137 | "worked_in_research": true|false, 138 | "worked_in_NLP": true|false, 139 | "agreed_to_terms_and_conditions": true 140 | "creation_date": , 141 | } 142 | ``` 143 | 144 | N.B. Historic changes concerning the evaluation of the machine translated sentences are logged (when sentences are evaluated and whether the participants change their mind). 145 | 146 | 147 | 148 | 200 | 201 | 202 | 203 | 204 | 205 | 206 | 207 | 208 | -------------------------------------------------------------------------------- /DiaBLa-corpus/dialogues/2018-05-17T10-57-19.461882_french_english_58_59.json: -------------------------------------------------------------------------------- 1 | { 2 | "start_time": "2018-05-17T10:57:19.461882", 3 | "end_time": null, 4 | "scenario": [ 5 | [ 6 | "You are in a classroom.", 7 | "Vous \u00eates dans une salle de classe." 8 | ], 9 | [ 10 | "You are the teacher and you are talking to a student.", 11 | "Vous \u00eates le ou la professeur(e) et vous discutez avec un(e) \u00e9l\u00e8ve(e) ou \u00e9tudiant(e)." 12 | ], 13 | [ 14 | "You are the student and you are talking to your teacher.", 15 | "Vous \u00eates un(e) \u00e9l\u00e8ve(e) ou \u00e9tudiant(e) et vous discutez avec votre professeur(e)." 16 | ] 17 | ], 18 | "user1": { 19 | "role_num": 2, 20 | "lang": "french", 21 | "role": [ 22 | "You are the student and you are talking to your teacher.", 23 | "Vous \u00eates un(e) \u00e9l\u00e8ve(e) ou \u00e9tudiant(e) et vous discutez avec votre professeur(e)." 24 | ], 25 | "initiated_dialogue": true, 26 | "turn_number": 1, 27 | "useragent": "Mozilla/5.0 (X11; Linux x86_64; rv:62.0) Gecko/20100101 Firefox/62.0", 28 | "eval-stage": true 29 | }, 30 | "user2": { 31 | "lang": "english", 32 | "role": [ 33 | "You are the teacher and you are talking to a student.", 34 | "Vous \u00eates le ou la professeur(e) et vous discutez avec un(e) \u00e9l\u00e8ve(e) ou \u00e9tudiant(e)." 35 | ], 36 | "rolenum": 1, 37 | "initiated_dialogue": false, 38 | "turn_number": 2, 39 | "useragent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.183 Safari/537.36 Vivaldi/1.96.1147.42", 40 | "eval-stage": true 41 | }, 42 | "translation_model": "baseline", 43 | "utterances": { 44 | "0": { 45 | "language": "french", 46 | "original_text": "Madame, est-ce qu'on fera bient\u00f4t un contr\u00f4le", 47 | "preprocessed_text": "madame , est @-@ ce qu' on fera bient\u00f4t un contr\u00f4le", 48 | "translated_text": "ma 'am , are we going to be in control soon ?", 49 | "postprocessed_text": "Ma'am, are we going to be in control soon?", 50 | "composition_time": "2018-05-17T10:58:20.669968", 51 | "preprocessing_begin": "2018-05-17T10:58:20.753567", 52 | "preprocessing_end": "2018-05-17T10:58:23.377538", 53 | "translation_begin": "2018-05-17T10:58:23.377748", 54 | "translation_end": "2018-05-17T10:58:24.432793", 55 | "postprocessing_begin": "2018-05-17T10:58:24.433282", 56 | "postprocessing_end": "2018-05-17T10:58:24.494011", 57 | "sent_time": "2018-05-17T10:58:24.496198", 58 | "eval": { 59 | "judgment_history": [ 60 | [ 61 | "medium", 62 | "2018-05-17T10:59:05.753293" 63 | ] 64 | ], 65 | "judgment": "medium", 66 | "problems": [ 67 | "word choice", 68 | "coherence" 69 | ], 70 | "verbatim": "", 71 | "problem_history": [ 72 | [ 73 | "word choice", 74 | "2018-05-17T10:59:09.448963", 75 | true 76 | ], 77 | [ 78 | "coherence", 79 | "2018-05-17T10:59:10.307157", 80 | true 81 | ] 82 | ], 83 | "verbatim_history": [] 84 | }, 85 | "reference_translation": "Miss, will there be a test soon?", 86 | "normalised_version": "Madame, est-ce qu'on fera bient\u00f4t un contr\u00f4le ?" 87 | }, 88 | "1": { 89 | "language": "english", 90 | "original_text": "What would you like to be in control of?", 91 | "preprocessed_text": "what would you like to be in control of ?", 92 | "translated_text": "qu' est @-@ ce que tu veux contr\u00f4ler ?", 93 | "postprocessed_text": "Qu'est-ce que tu veux contr\u00f4ler ?", 94 | "composition_time": "2018-05-17T10:58:39.179329", 95 | "preprocessing_begin": "2018-05-17T10:58:39.242928", 96 | "preprocessing_end": "2018-05-17T10:58:41.551865", 97 | "translation_begin": "2018-05-17T10:58:41.551957", 98 | "translation_end": "2018-05-17T10:58:42.477216", 99 | "postprocessing_begin": "2018-05-17T10:58:42.477772", 100 | "postprocessing_end": "2018-05-17T10:58:42.531082", 101 | "sent_time": "2018-05-17T10:58:42.532425", 102 | "eval": { 103 | "judgment_history": [ 104 | [ 105 | "medium", 106 | "2018-05-17T10:59:38.633012" 107 | ] 108 | ], 109 | "judgment": "medium", 110 | "problems": [], 111 | "verbatim": "Peu en ra", 112 | "problem_history": [ 113 | [ 114 | "coherence", 115 | "2018-05-17T10:59:41.347300", 116 | true 117 | ], 118 | [ 119 | "coherence", 120 | "2018-05-17T11:00:09.474486", 121 | false 122 | ] 123 | ], 124 | "verbatim_history": [ 125 | [ 126 | "Peu en ra", 127 | "2018-05-17T11:00:06.016462", 128 | "2018-05-17T11:00:06.016462" 129 | ] 130 | ] 131 | }, 132 | "reference_translation": "Qu\u2019est-ce que vous voudriez contr\u00f4ler ?", 133 | "normalised_version": "" 134 | }, 135 | "2": { 136 | "language": "french", 137 | "original_text": "Un contr\u00f4le sur le dernier chapitre.", 138 | "preprocessed_text": "un contr\u00f4le sur le dernier chapitre .", 139 | "translated_text": "a control on the last chapter .", 140 | "postprocessed_text": "A control on the last chapter.", 141 | "composition_time": "2018-05-17T10:59:19.829432", 142 | "preprocessing_begin": "2018-05-17T10:59:19.898160", 143 | "preprocessing_end": "2018-05-17T10:59:22.492664", 144 | "translation_begin": "2018-05-17T10:59:22.492818", 145 | "translation_end": "2018-05-17T10:59:24.490765", 146 | "postprocessing_begin": "2018-05-17T10:59:24.491940", 147 | "postprocessing_end": "2018-05-17T10:59:24.558796", 148 | "sent_time": "2018-05-17T10:59:24.561714", 149 | "eval": { 150 | "judgment_history": [ 151 | [ 152 | "medium", 153 | "2018-05-17T10:59:35.260667" 154 | ] 155 | ], 156 | "judgment": "medium", 157 | "problems": [ 158 | "word choice" 159 | ], 160 | "verbatim": "", 161 | "problem_history": [ 162 | [ 163 | "word choice", 164 | "2018-05-17T10:59:37.091662", 165 | true 166 | ] 167 | ], 168 | "verbatim_history": [] 169 | }, 170 | "reference_translation": "A test on the last chapter.", 171 | "normalised_version": "" 172 | }, 173 | "3": { 174 | "language": "french", 175 | "original_text": "J'aimerais savoir combien de temps il me reste pour r\u00e9viser.", 176 | "preprocessed_text": "j' aimerais savoir combien de temps il me reste pour r\u00e9viser .", 177 | "translated_text": "I 'd like to know how much time I have left to study .", 178 | "postprocessed_text": "I'd like to know how much time I have left to study.", 179 | "composition_time": "2018-05-17T10:59:19.829432", 180 | "preprocessing_begin": "2018-05-17T10:59:19.898160", 181 | "preprocessing_end": "2018-05-17T10:59:22.492664", 182 | "translation_begin": "2018-05-17T10:59:22.492818", 183 | "translation_end": "2018-05-17T10:59:24.490765", 184 | "postprocessing_begin": "2018-05-17T10:59:24.491940", 185 | "postprocessing_end": "2018-05-17T10:59:24.558796", 186 | "sent_time": "2018-05-17T10:59:24.563213", 187 | "eval": { 188 | "judgment_history": [ 189 | [ 190 | "perfect", 191 | "2018-05-17T11:00:20.726286" 192 | ] 193 | ], 194 | "judgment": "perfect", 195 | "problems": [], 196 | "verbatim": "", 197 | "problem_history": [], 198 | "verbatim_history": [] 199 | }, 200 | "reference_translation": "I\u2019d like to know how long I have left to revise.", 201 | "normalised_version": "" 202 | }, 203 | "4": { 204 | "language": "english", 205 | "original_text": "We will have an exam, if that is what you mean, next week on Thursday", 206 | "preprocessed_text": "we will have an exam , if that is what you mean , next week on Thursday", 207 | "translated_text": "nous aurons un examen , si c' est ce que vous voulez dire , la semaine prochaine , jeudi prochain .", 208 | "postprocessed_text": "Nous aurons un examen, si c'est ce que vous voulez dire, la semaine prochaine, jeudi prochain.", 209 | "composition_time": "2018-05-17T10:59:55.942868", 210 | "preprocessing_begin": "2018-05-17T10:59:56.000569", 211 | "preprocessing_end": "2018-05-17T10:59:58.276586", 212 | "translation_begin": "2018-05-17T10:59:58.276685", 213 | "translation_end": "2018-05-17T11:00:00.331973", 214 | "postprocessing_begin": "2018-05-17T11:00:00.332486", 215 | "postprocessing_end": "2018-05-17T11:00:00.382489", 216 | "sent_time": "2018-05-17T11:00:00.384762", 217 | "eval": { 218 | "judgment_history": [ 219 | [ 220 | "perfect", 221 | "2018-05-17T11:00:10.472490" 222 | ] 223 | ], 224 | "judgment": "perfect", 225 | "problems": [], 226 | "verbatim": "", 227 | "problem_history": [], 228 | "verbatim_history": [] 229 | }, 230 | "reference_translation": "Nous allons faire un contr\u00f4le, si c\u2019est ce que tu voulais dire, le jeudi de la semaine prochaine.", 231 | "normalised_version": "We will have an exam, if that is what you mean, next week on Thursday." 232 | }, 233 | "5": { 234 | "language": "english", 235 | "original_text": "We will cover all the material up to next Tuesday, so start studying soon!", 236 | "preprocessed_text": "we will cover all the material up to next Tuesday , so start studying soon !", 237 | "translated_text": "nous couvri@@ rons tout le mat\u00e9riel jusqu' \u00e0 mardi prochain , alors commence \u00e0 \u00e9tudier bient\u00f4t !", 238 | "postprocessed_text": "Nous couvrirons tout le mat\u00e9riel jusqu'\u00e0 mardi prochain, alors commence \u00e0 \u00e9tudier bient\u00f4t !", 239 | "composition_time": "2018-05-17T11:00:13.532004", 240 | "preprocessing_begin": "2018-05-17T11:00:13.594791", 241 | "preprocessing_end": "2018-05-17T11:00:15.975803", 242 | "translation_begin": "2018-05-17T11:00:15.975916", 243 | "translation_end": "2018-05-17T11:00:17.407267", 244 | "postprocessing_begin": "2018-05-17T11:00:17.407666", 245 | "postprocessing_end": "2018-05-17T11:00:17.446555", 246 | "sent_time": "2018-05-17T11:00:17.448110", 247 | "eval": { 248 | "judgment_history": [ 249 | [ 250 | "medium", 251 | "2018-05-17T11:00:21.095774" 252 | ] 253 | ], 254 | "judgment": "medium", 255 | "problems": [ 256 | "word choice" 257 | ], 258 | "verbatim": "", 259 | "problem_history": [ 260 | [ 261 | "word choice", 262 | "2018-05-17T11:00:22.772342", 263 | true 264 | ] 265 | ], 266 | "verbatim_history": [] 267 | }, 268 | "reference_translation": "Il portera sur tout ce que nous aurons \u00e9tudi\u00e9 d\u2019ici mardi prochain, donc commencez bient\u00f4t \u00e0 r\u00e9viser.", 269 | "normalised_version": "" 270 | }, 271 | "6": { 272 | "language": "french", 273 | "original_text": "D'accord, si j'ai des questions, est-ce que je pourrais vous les poser par email ?", 274 | "preprocessed_text": "d' accord , si j' ai des questions , est @-@ ce que je pourrais vous les poser par email ?", 275 | "translated_text": "okay , if I have any questions , could I email them to you ?", 276 | "postprocessed_text": "Okay, if I have any questions, could I email them to you?", 277 | "composition_time": "2018-05-17T11:00:45.482844", 278 | "preprocessing_begin": "2018-05-17T11:00:45.546401", 279 | "preprocessing_end": "2018-05-17T11:00:47.963475", 280 | "translation_begin": "2018-05-17T11:00:47.963629", 281 | "translation_end": "2018-05-17T11:00:49.364142", 282 | "postprocessing_begin": "2018-05-17T11:00:49.364449", 283 | "postprocessing_end": "2018-05-17T11:00:49.417914", 284 | "sent_time": "2018-05-17T11:00:49.419624", 285 | "eval": { 286 | "judgment_history": [ 287 | [ 288 | "perfect", 289 | "2018-05-17T11:01:21.002056" 290 | ] 291 | ], 292 | "judgment": "perfect", 293 | "problems": [], 294 | "verbatim": "", 295 | "problem_history": [], 296 | "verbatim_history": [] 297 | }, 298 | "reference_translation": "Ok, if I have any questions, can I ask you them by email?", 299 | "normalised_version": "" 300 | }, 301 | "7": { 302 | "language": "english", 303 | "original_text": "Of course!", 304 | "preprocessed_text": "of course !", 305 | "translated_text": "bien s\u00fbr !", 306 | "postprocessed_text": "Bien s\u00fbr !", 307 | "composition_time": "2018-05-17T11:01:16.306217", 308 | "preprocessing_begin": "2018-05-17T11:01:16.360278", 309 | "preprocessing_end": "2018-05-17T11:01:18.707148", 310 | "translation_begin": "2018-05-17T11:01:18.707331", 311 | "translation_end": "2018-05-17T11:01:20.956965", 312 | "postprocessing_begin": "2018-05-17T11:01:20.957409", 313 | "postprocessing_end": "2018-05-17T11:01:20.995112", 314 | "sent_time": "2018-05-17T11:01:20.996700", 315 | "eval": { 316 | "judgment_history": [ 317 | [ 318 | "perfect", 319 | "2018-05-17T11:01:27.229683" 320 | ] 321 | ], 322 | "judgment": "perfect", 323 | "problems": [], 324 | "verbatim": "", 325 | "problem_history": [], 326 | "verbatim_history": [] 327 | }, 328 | "reference_translation": "Bien s\u00fbr !", 329 | "normalised_version": "" 330 | }, 331 | "8": { 332 | "language": "english", 333 | "original_text": "But I will only answer emails during working hours, so please don't send them late on Wednesday evening.", 334 | "preprocessed_text": "but I will only answer emails during working hours , so please don 't send them late on Wednesday evening .", 335 | "translated_text": "mais je ne r\u00e9pondrai qu' aux mails pendant les heures de travail , alors ne les envoyez pas tard mercredi soir .", 336 | "postprocessed_text": "Mais je ne r\u00e9pondrai qu'aux mails pendant les heures de travail, alors ne les envoyez pas tard mercredi soir.", 337 | "composition_time": "2018-05-17T11:01:16.306217", 338 | "preprocessing_begin": "2018-05-17T11:01:16.360278", 339 | "preprocessing_end": "2018-05-17T11:01:18.707148", 340 | "translation_begin": "2018-05-17T11:01:18.707331", 341 | "translation_end": "2018-05-17T11:01:20.956965", 342 | "postprocessing_begin": "2018-05-17T11:01:20.957409", 343 | "postprocessing_end": "2018-05-17T11:01:20.995112", 344 | "sent_time": "2018-05-17T11:01:20.997752", 345 | "eval": { 346 | "judgment_history": [ 347 | [ 348 | "perfect", 349 | "2018-05-17T11:01:28.118812" 350 | ] 351 | ], 352 | "judgment": "perfect", 353 | "problems": [], 354 | "verbatim": "", 355 | "problem_history": [], 356 | "verbatim_history": [] 357 | }, 358 | "reference_translation": "Mais je r\u00e9pondrai uniquement aux e-mails pendant les heures de travail, donc merci de ne pas les envoyer tard mercredi soir.", 359 | "normalised_version": "" 360 | }, 361 | "9": { 362 | "language": "french", 363 | "original_text": "Merci madame, j'y ferai attention", 364 | "preprocessed_text": "merci madame , j' y ferai attention", 365 | "translated_text": "thank you , ma 'am .", 366 | "postprocessed_text": "Thank you, ma'am.", 367 | "composition_time": "2018-05-17T11:01:57.069503", 368 | "preprocessing_begin": "2018-05-17T11:01:57.144686", 369 | "preprocessing_end": "2018-05-17T11:01:59.558710", 370 | "translation_begin": "2018-05-17T11:01:59.558837", 371 | "translation_end": "2018-05-17T11:02:00.596495", 372 | "postprocessing_begin": "2018-05-17T11:02:00.597081", 373 | "postprocessing_end": "2018-05-17T11:02:00.657251", 374 | "sent_time": "2018-05-17T11:02:00.659565", 375 | "eval": { 376 | "judgment_history": [ 377 | [ 378 | "perfect", 379 | "2018-05-17T11:02:12.461812" 380 | ] 381 | ], 382 | "judgment": "perfect", 383 | "problems": [], 384 | "verbatim": "", 385 | "problem_history": [], 386 | "verbatim_history": [] 387 | }, 388 | "reference_translation": "Thank you Miss! I\u2019ll try to do that!", 389 | "normalised_version": "Merci madame, j'y ferai attention." 390 | } 391 | }, 392 | "final_evaluation_user1": { 393 | "style": "good", 394 | "would_use": true, 395 | "grammaticality": "excellent", 396 | "verbatim_quality": "", 397 | "meaning": "good", 398 | "particular_problems": "", 399 | "interface": "", 400 | "tech": "There were no technical problems", 401 | "coherence": "good", 402 | "timestamp": "2018-05-17T11:02:30.038849", 403 | "word_choice": "average", 404 | "technical_issue": "There were no technical problems" 405 | }, 406 | "final_evaluation_user2": { 407 | "style": "good", 408 | "would_use": true, 409 | "grammaticality": "excellent", 410 | "verbatim_quality": "there was one vital mistranslation at the beginning (exam as 'control') that needed to be cleared up, but the rest was fine.", 411 | "meaning": "poor", 412 | "particular_problems": "'control' for 'exam'", 413 | "interface": "maybe give a reminder about the evaluation of translations, for everyone who doesn't read instructions?", 414 | "tech": "There were no technical problems", 415 | "coherence": "good", 416 | "timestamp": "2018-05-17T11:04:43.261254", 417 | "word_choice": "poor", 418 | "technical_issue": "There were no technical problems" 419 | }, 420 | "fr_transl": true 421 | } -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Attribution-ShareAlike 4.0 International 2 | 3 | ======================================================================= 4 | 5 | Creative Commons Corporation ("Creative Commons") is not a law firm and 6 | does not provide legal services or legal advice. Distribution of 7 | Creative Commons public licenses does not create a lawyer-client or 8 | other relationship. Creative Commons makes its licenses and related 9 | information available on an "as-is" basis. Creative Commons gives no 10 | warranties regarding its licenses, any material licensed under their 11 | terms and conditions, or any related information. Creative Commons 12 | disclaims all liability for damages resulting from their use to the 13 | fullest extent possible. 14 | 15 | Using Creative Commons Public Licenses 16 | 17 | Creative Commons public licenses provide a standard set of terms and 18 | conditions that creators and other rights holders may use to share 19 | original works of authorship and other material subject to copyright 20 | and certain other rights specified in the public license below. The 21 | following considerations are for informational purposes only, are not 22 | exhaustive, and do not form part of our licenses. 23 | 24 | Considerations for licensors: Our public licenses are 25 | intended for use by those authorized to give the public 26 | permission to use material in ways otherwise restricted by 27 | copyright and certain other rights. Our licenses are 28 | irrevocable. Licensors should read and understand the terms 29 | and conditions of the license they choose before applying it. 30 | Licensors should also secure all rights necessary before 31 | applying our licenses so that the public can reuse the 32 | material as expected. Licensors should clearly mark any 33 | material not subject to the license. This includes other CC- 34 | licensed material, or material used under an exception or 35 | limitation to copyright. More considerations for licensors: 36 | wiki.creativecommons.org/Considerations_for_licensors 37 | 38 | Considerations for the public: By using one of our public 39 | licenses, a licensor grants the public permission to use the 40 | licensed material under specified terms and conditions. If 41 | the licensor's permission is not necessary for any reason--for 42 | example, because of any applicable exception or limitation to 43 | copyright--then that use is not regulated by the license. Our 44 | licenses grant only permissions under copyright and certain 45 | other rights that a licensor has authority to grant. Use of 46 | the licensed material may still be restricted for other 47 | reasons, including because others have copyright or other 48 | rights in the material. A licensor may make special requests, 49 | such as asking that all changes be marked or described. 50 | Although not required by our licenses, you are encouraged to 51 | respect those requests where reasonable. More considerations 52 | for the public: 53 | wiki.creativecommons.org/Considerations_for_licensees 54 | 55 | ======================================================================= 56 | 57 | Creative Commons Attribution-ShareAlike 4.0 International Public 58 | License 59 | 60 | By exercising the Licensed Rights (defined below), You accept and agree 61 | to be bound by the terms and conditions of this Creative Commons 62 | Attribution-ShareAlike 4.0 International Public License ("Public 63 | License"). To the extent this Public License may be interpreted as a 64 | contract, You are granted the Licensed Rights in consideration of Your 65 | acceptance of these terms and conditions, and the Licensor grants You 66 | such rights in consideration of benefits the Licensor receives from 67 | making the Licensed Material available under these terms and 68 | conditions. 69 | 70 | 71 | Section 1 -- Definitions. 72 | 73 | a. Adapted Material means material subject to Copyright and Similar 74 | Rights that is derived from or based upon the Licensed Material 75 | and in which the Licensed Material is translated, altered, 76 | arranged, transformed, or otherwise modified in a manner requiring 77 | permission under the Copyright and Similar Rights held by the 78 | Licensor. For purposes of this Public License, where the Licensed 79 | Material is a musical work, performance, or sound recording, 80 | Adapted Material is always produced where the Licensed Material is 81 | synched in timed relation with a moving image. 82 | 83 | b. Adapter's License means the license You apply to Your Copyright 84 | and Similar Rights in Your contributions to Adapted Material in 85 | accordance with the terms and conditions of this Public License. 86 | 87 | c. BY-SA Compatible License means a license listed at 88 | creativecommons.org/compatiblelicenses, approved by Creative 89 | Commons as essentially the equivalent of this Public License. 90 | 91 | d. Copyright and Similar Rights means copyright and/or similar rights 92 | closely related to copyright including, without limitation, 93 | performance, broadcast, sound recording, and Sui Generis Database 94 | Rights, without regard to how the rights are labeled or 95 | categorized. For purposes of this Public License, the rights 96 | specified in Section 2(b)(1)-(2) are not Copyright and Similar 97 | Rights. 98 | 99 | e. Effective Technological Measures means those measures that, in the 100 | absence of proper authority, may not be circumvented under laws 101 | fulfilling obligations under Article 11 of the WIPO Copyright 102 | Treaty adopted on December 20, 1996, and/or similar international 103 | agreements. 104 | 105 | f. Exceptions and Limitations means fair use, fair dealing, and/or 106 | any other exception or limitation to Copyright and Similar Rights 107 | that applies to Your use of the Licensed Material. 108 | 109 | g. License Elements means the license attributes listed in the name 110 | of a Creative Commons Public License. The License Elements of this 111 | Public License are Attribution and ShareAlike. 112 | 113 | h. Licensed Material means the artistic or literary work, database, 114 | or other material to which the Licensor applied this Public 115 | License. 116 | 117 | i. Licensed Rights means the rights granted to You subject to the 118 | terms and conditions of this Public License, which are limited to 119 | all Copyright and Similar Rights that apply to Your use of the 120 | Licensed Material and that the Licensor has authority to license. 121 | 122 | j. Licensor means the individual(s) or entity(ies) granting rights 123 | under this Public License. 124 | 125 | k. Share means to provide material to the public by any means or 126 | process that requires permission under the Licensed Rights, such 127 | as reproduction, public display, public performance, distribution, 128 | dissemination, communication, or importation, and to make material 129 | available to the public including in ways that members of the 130 | public may access the material from a place and at a time 131 | individually chosen by them. 132 | 133 | l. Sui Generis Database Rights means rights other than copyright 134 | resulting from Directive 96/9/EC of the European Parliament and of 135 | the Council of 11 March 1996 on the legal protection of databases, 136 | as amended and/or succeeded, as well as other essentially 137 | equivalent rights anywhere in the world. 138 | 139 | m. You means the individual or entity exercising the Licensed Rights 140 | under this Public License. Your has a corresponding meaning. 141 | 142 | 143 | Section 2 -- Scope. 144 | 145 | a. License grant. 146 | 147 | 1. Subject to the terms and conditions of this Public License, 148 | the Licensor hereby grants You a worldwide, royalty-free, 149 | non-sublicensable, non-exclusive, irrevocable license to 150 | exercise the Licensed Rights in the Licensed Material to: 151 | 152 | a. reproduce and Share the Licensed Material, in whole or 153 | in part; and 154 | 155 | b. produce, reproduce, and Share Adapted Material. 156 | 157 | 2. Exceptions and Limitations. For the avoidance of doubt, where 158 | Exceptions and Limitations apply to Your use, this Public 159 | License does not apply, and You do not need to comply with 160 | its terms and conditions. 161 | 162 | 3. Term. The term of this Public License is specified in Section 163 | 6(a). 164 | 165 | 4. Media and formats; technical modifications allowed. The 166 | Licensor authorizes You to exercise the Licensed Rights in 167 | all media and formats whether now known or hereafter created, 168 | and to make technical modifications necessary to do so. The 169 | Licensor waives and/or agrees not to assert any right or 170 | authority to forbid You from making technical modifications 171 | necessary to exercise the Licensed Rights, including 172 | technical modifications necessary to circumvent Effective 173 | Technological Measures. For purposes of this Public License, 174 | simply making modifications authorized by this Section 2(a) 175 | (4) never produces Adapted Material. 176 | 177 | 5. Downstream recipients. 178 | 179 | a. Offer from the Licensor -- Licensed Material. Every 180 | recipient of the Licensed Material automatically 181 | receives an offer from the Licensor to exercise the 182 | Licensed Rights under the terms and conditions of this 183 | Public License. 184 | 185 | b. Additional offer from the Licensor -- Adapted Material. 186 | Every recipient of Adapted Material from You 187 | automatically receives an offer from the Licensor to 188 | exercise the Licensed Rights in the Adapted Material 189 | under the conditions of the Adapter's License You apply. 190 | 191 | c. No downstream restrictions. You may not offer or impose 192 | any additional or different terms or conditions on, or 193 | apply any Effective Technological Measures to, the 194 | Licensed Material if doing so restricts exercise of the 195 | Licensed Rights by any recipient of the Licensed 196 | Material. 197 | 198 | 6. No endorsement. Nothing in this Public License constitutes or 199 | may be construed as permission to assert or imply that You 200 | are, or that Your use of the Licensed Material is, connected 201 | with, or sponsored, endorsed, or granted official status by, 202 | the Licensor or others designated to receive attribution as 203 | provided in Section 3(a)(1)(A)(i). 204 | 205 | b. Other rights. 206 | 207 | 1. Moral rights, such as the right of integrity, are not 208 | licensed under this Public License, nor are publicity, 209 | privacy, and/or other similar personality rights; however, to 210 | the extent possible, the Licensor waives and/or agrees not to 211 | assert any such rights held by the Licensor to the limited 212 | extent necessary to allow You to exercise the Licensed 213 | Rights, but not otherwise. 214 | 215 | 2. Patent and trademark rights are not licensed under this 216 | Public License. 217 | 218 | 3. To the extent possible, the Licensor waives any right to 219 | collect royalties from You for the exercise of the Licensed 220 | Rights, whether directly or through a collecting society 221 | under any voluntary or waivable statutory or compulsory 222 | licensing scheme. In all other cases the Licensor expressly 223 | reserves any right to collect such royalties. 224 | 225 | 226 | Section 3 -- License Conditions. 227 | 228 | Your exercise of the Licensed Rights is expressly made subject to the 229 | following conditions. 230 | 231 | a. Attribution. 232 | 233 | 1. If You Share the Licensed Material (including in modified 234 | form), You must: 235 | 236 | a. retain the following if it is supplied by the Licensor 237 | with the Licensed Material: 238 | 239 | i. identification of the creator(s) of the Licensed 240 | Material and any others designated to receive 241 | attribution, in any reasonable manner requested by 242 | the Licensor (including by pseudonym if 243 | designated); 244 | 245 | ii. a copyright notice; 246 | 247 | iii. a notice that refers to this Public License; 248 | 249 | iv. a notice that refers to the disclaimer of 250 | warranties; 251 | 252 | v. a URI or hyperlink to the Licensed Material to the 253 | extent reasonably practicable; 254 | 255 | b. indicate if You modified the Licensed Material and 256 | retain an indication of any previous modifications; and 257 | 258 | c. indicate the Licensed Material is licensed under this 259 | Public License, and include the text of, or the URI or 260 | hyperlink to, this Public License. 261 | 262 | 2. You may satisfy the conditions in Section 3(a)(1) in any 263 | reasonable manner based on the medium, means, and context in 264 | which You Share the Licensed Material. For example, it may be 265 | reasonable to satisfy the conditions by providing a URI or 266 | hyperlink to a resource that includes the required 267 | information. 268 | 269 | 3. If requested by the Licensor, You must remove any of the 270 | information required by Section 3(a)(1)(A) to the extent 271 | reasonably practicable. 272 | 273 | b. ShareAlike. 274 | 275 | In addition to the conditions in Section 3(a), if You Share 276 | Adapted Material You produce, the following conditions also apply. 277 | 278 | 1. The Adapter's License You apply must be a Creative Commons 279 | license with the same License Elements, this version or 280 | later, or a BY-SA Compatible License. 281 | 282 | 2. You must include the text of, or the URI or hyperlink to, the 283 | Adapter's License You apply. You may satisfy this condition 284 | in any reasonable manner based on the medium, means, and 285 | context in which You Share Adapted Material. 286 | 287 | 3. You may not offer or impose any additional or different terms 288 | or conditions on, or apply any Effective Technological 289 | Measures to, Adapted Material that restrict exercise of the 290 | rights granted under the Adapter's License You apply. 291 | 292 | 293 | Section 4 -- Sui Generis Database Rights. 294 | 295 | Where the Licensed Rights include Sui Generis Database Rights that 296 | apply to Your use of the Licensed Material: 297 | 298 | a. for the avoidance of doubt, Section 2(a)(1) grants You the right 299 | to extract, reuse, reproduce, and Share all or a substantial 300 | portion of the contents of the database; 301 | 302 | b. if You include all or a substantial portion of the database 303 | contents in a database in which You have Sui Generis Database 304 | Rights, then the database in which You have Sui Generis Database 305 | Rights (but not its individual contents) is Adapted Material, 306 | 307 | including for purposes of Section 3(b); and 308 | c. You must comply with the conditions in Section 3(a) if You Share 309 | all or a substantial portion of the contents of the database. 310 | 311 | For the avoidance of doubt, this Section 4 supplements and does not 312 | replace Your obligations under this Public License where the Licensed 313 | Rights include other Copyright and Similar Rights. 314 | 315 | 316 | Section 5 -- Disclaimer of Warranties and Limitation of Liability. 317 | 318 | a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE 319 | EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS 320 | AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF 321 | ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS, 322 | IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION, 323 | WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR 324 | PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS, 325 | ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT 326 | KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT 327 | ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU. 328 | 329 | b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE 330 | TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION, 331 | NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT, 332 | INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES, 333 | COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR 334 | USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN 335 | ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR 336 | DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR 337 | IN PART, THIS LIMITATION MAY NOT APPLY TO YOU. 338 | 339 | c. The disclaimer of warranties and limitation of liability provided 340 | above shall be interpreted in a manner that, to the extent 341 | possible, most closely approximates an absolute disclaimer and 342 | waiver of all liability. 343 | 344 | 345 | Section 6 -- Term and Termination. 346 | 347 | a. This Public License applies for the term of the Copyright and 348 | Similar Rights licensed here. However, if You fail to comply with 349 | this Public License, then Your rights under this Public License 350 | terminate automatically. 351 | 352 | b. Where Your right to use the Licensed Material has terminated under 353 | Section 6(a), it reinstates: 354 | 355 | 1. automatically as of the date the violation is cured, provided 356 | it is cured within 30 days of Your discovery of the 357 | violation; or 358 | 359 | 2. upon express reinstatement by the Licensor. 360 | 361 | For the avoidance of doubt, this Section 6(b) does not affect any 362 | right the Licensor may have to seek remedies for Your violations 363 | of this Public License. 364 | 365 | c. For the avoidance of doubt, the Licensor may also offer the 366 | Licensed Material under separate terms or conditions or stop 367 | distributing the Licensed Material at any time; however, doing so 368 | will not terminate this Public License. 369 | 370 | d. Sections 1, 5, 6, 7, and 8 survive termination of this Public 371 | License. 372 | 373 | 374 | Section 7 -- Other Terms and Conditions. 375 | 376 | a. The Licensor shall not be bound by any additional or different 377 | terms or conditions communicated by You unless expressly agreed. 378 | 379 | b. Any arrangements, understandings, or agreements regarding the 380 | Licensed Material not stated herein are separate from and 381 | independent of the terms and conditions of this Public License. 382 | 383 | 384 | Section 8 -- Interpretation. 385 | 386 | a. For the avoidance of doubt, this Public License does not, and 387 | shall not be interpreted to, reduce, limit, restrict, or impose 388 | conditions on any use of the Licensed Material that could lawfully 389 | be made without permission under this Public License. 390 | 391 | b. To the extent possible, if any provision of this Public License is 392 | deemed unenforceable, it shall be automatically reformed to the 393 | minimum extent necessary to make it enforceable. If the provision 394 | cannot be reformed, it shall be severed from this Public License 395 | without affecting the enforceability of the remaining terms and 396 | conditions. 397 | 398 | c. No term or condition of this Public License will be waived and no 399 | failure to comply consented to unless expressly agreed to by the 400 | Licensor. 401 | 402 | d. Nothing in this Public License constitutes or may be interpreted 403 | as a limitation upon, or waiver of, any privileges and immunities 404 | that apply to the Licensor or You, including from the legal 405 | processes of any jurisdiction or authority. 406 | 407 | 408 | ======================================================================= 409 | 410 | Creative Commons is not a party to its public 411 | licenses. Notwithstanding, Creative Commons may elect to apply one of 412 | its public licenses to material it publishes and in those instances 413 | will be considered the “Licensor.” The text of the Creative Commons 414 | public licenses is dedicated to the public domain under the CC0 Public 415 | Domain Dedication. Except for the limited purpose of indicating that 416 | material is shared under a Creative Commons public license or as 417 | otherwise permitted by the Creative Commons policies published at 418 | creativecommons.org/policies, Creative Commons does not authorize the 419 | use of the trademark "Creative Commons" or any other trademark or logo 420 | of Creative Commons without its prior written consent including, 421 | without limitation, in connection with any unauthorized modifications 422 | to any of its public licenses or any other arrangements, 423 | understandings, or agreements concerning use of licensed material. For 424 | the avoidance of doubt, this paragraph does not form part of the 425 | public licenses. 426 | 427 | Creative Commons may be contacted at creativecommons.org. 428 | -------------------------------------------------------------------------------- /DiaBLa-corpus/all-users.json: -------------------------------------------------------------------------------- 1 | { 2 | "user-20": { 3 | "age": "18-24", 4 | "idnum": 20, 5 | "gender": "female", 6 | "creation_date": "2018-05-01T11:15:03.938877", 7 | "english_ability": "native", 8 | "otherlangs": "", 9 | "french_ability": "poor", 10 | "worked_in_research": false, 11 | "worked_in_NLP": false, 12 | "agreed_to_terms_and_conditions": true 13 | }, 14 | "user-77": { 15 | "gender": "female", 16 | "english_ability": "native", 17 | "otherlangs": "spanish, afrikaans", 18 | "age": "35-44", 19 | "idnum": 77, 20 | "creation_date": "2018-05-21T20:46:24.095121", 21 | "french_ability": "none", 22 | "worked_in_research": true, 23 | "worked_in_NLP": true, 24 | "agreed_to_terms_and_conditions": true 25 | }, 26 | "user-61": { 27 | "age": "45-54", 28 | "idnum": 61, 29 | "gender": "male", 30 | "creation_date": "2018-05-17T11:28:51.158690", 31 | "english_ability": "good", 32 | "otherlangs": "arabe", 33 | "french_ability": "native", 34 | "worked_in_research": true, 35 | "worked_in_NLP": true, 36 | "agreed_to_terms_and_conditions": true 37 | }, 38 | "user-36": { 39 | "age": "55-64", 40 | "idnum": 36, 41 | "gender": "female", 42 | "creation_date": "2018-05-05T12:21:51.443415", 43 | "english_ability": "native", 44 | "otherlangs": "", 45 | "french_ability": "poor", 46 | "worked_in_research": false, 47 | "worked_in_NLP": false, 48 | "agreed_to_terms_and_conditions": true 49 | }, 50 | "user-41": { 51 | "age": "55-64", 52 | "gender": "male", 53 | "idnum": 41, 54 | "otherlangs": "arabic", 55 | "creation_date": "2018-05-08T19:06:59.794483", 56 | "french_ability": "medium", 57 | "english_ability": "native", 58 | "worked_in_research": false, 59 | "worked_in_NLP": false, 60 | "agreed_to_terms_and_conditions": true 61 | }, 62 | "user-16": { 63 | "english_ability": "poor", 64 | "otherlangs": "portugais (br\u00e9sil)", 65 | "age": "65-74", 66 | "idnum": 16, 67 | "creation_date": "2018-04-30T10:10:01.284911", 68 | "french_ability": "native", 69 | "gender": "male", 70 | "worked_in_research": false, 71 | "worked_in_NLP": false, 72 | "agreed_to_terms_and_conditions": true 73 | }, 74 | "user-57": { 75 | "age": "25-34", 76 | "idnum": 57, 77 | "gender": "male", 78 | "creation_date": "2018-05-04T12:43:55.705713", 79 | "english_ability": "good", 80 | "otherlangs": "", 81 | "french_ability": "native", 82 | "worked_in_research": false, 83 | "worked_in_NLP": true, 84 | "agreed_to_terms_and_conditions": true 85 | }, 86 | "user-6": { 87 | "english_ability": "native", 88 | "otherlangs": "", 89 | "age": "55-64", 90 | "idnum": 6, 91 | "creation_date": "2018-04-27T09:05:01.484342", 92 | "french_ability": "poor", 93 | "gender": "female", 94 | "worked_in_research": false, 95 | "worked_in_NLP": false, 96 | "agreed_to_terms_and_conditions": true 97 | }, 98 | "user-7": { 99 | "gender": "male", 100 | "otherlangs": "", 101 | "english_ability": "good", 102 | "idnum": 7, 103 | "french_ability": "native", 104 | "age": "25-34", 105 | "creation_date": "2018-04-27T10:49:05.761531", 106 | "worked_in_research": true, 107 | "worked_in_NLP": true, 108 | "agreed_to_terms_and_conditions": true 109 | }, 110 | "user-56": { 111 | "age": "55-64", 112 | "idnum": 56, 113 | "gender": "female", 114 | "creation_date": "2018-05-15T18:58:26.117939", 115 | "english_ability": "native", 116 | "otherlangs": "", 117 | "french_ability": "poor", 118 | "worked_in_research": false, 119 | "worked_in_NLP": false, 120 | "agreed_to_terms_and_conditions": true 121 | }, 122 | "user-17": { 123 | "english_ability": "native", 124 | "otherlangs": "", 125 | "age": "55-64", 126 | "idnum": 17, 127 | "creation_date": "2018-04-27T16:57:00.520643", 128 | "french_ability": "poor", 129 | "gender": "female", 130 | "worked_in_research": false, 131 | "worked_in_NLP": false, 132 | "agreed_to_terms_and_conditions": true 133 | }, 134 | "user-40": { 135 | "age": "35-44", 136 | "gender": "female", 137 | "idnum": 40, 138 | "otherlangs": "", 139 | "creation_date": "2018-05-08T18:42:39.567200", 140 | "french_ability": "native", 141 | "english_ability": "good", 142 | "worked_in_research": true, 143 | "worked_in_NLP": false, 144 | "agreed_to_terms_and_conditions": true 145 | }, 146 | "user-37": { 147 | "age": "65-74", 148 | "gender": "female", 149 | "idnum": 37, 150 | "otherlangs": "", 151 | "creation_date": "2018-05-07T13:35:50.726778", 152 | "french_ability": "near-native", 153 | "english_ability": "native", 154 | "worked_in_research": false, 155 | "worked_in_NLP": false, 156 | "agreed_to_terms_and_conditions": true 157 | }, 158 | "user-60": { 159 | "age": "35-44", 160 | "idnum": 60, 161 | "gender": "male", 162 | "creation_date": "2018-05-17T11:13:36.994382", 163 | "english_ability": "good", 164 | "otherlangs": "german", 165 | "french_ability": "native", 166 | "worked_in_research": true, 167 | "worked_in_NLP": true, 168 | "agreed_to_terms_and_conditions": true 169 | }, 170 | "user-76": { 171 | "english_ability": "good", 172 | "otherlangs": "german", 173 | "age": "25-34", 174 | "idnum": 76, 175 | "creation_date": "2018-05-15T07:32:29.245082", 176 | "french_ability": "native", 177 | "gender": "male", 178 | "worked_in_research": false, 179 | "worked_in_NLP": false, 180 | "agreed_to_terms_and_conditions": true 181 | }, 182 | "user-21": { 183 | "age": "45-54", 184 | "gender": "male", 185 | "english_ability": "native", 186 | "idnum": 21, 187 | "otherlangs": "", 188 | "creation_date": "2018-05-01T12:52:36.913957", 189 | "french_ability": "poor", 190 | "worked_in_research": false, 191 | "worked_in_NLP": false, 192 | "agreed_to_terms_and_conditions": true 193 | }, 194 | "user-47": { 195 | "french_ability": "native", 196 | "gender": "female", 197 | "otherlangs": "", 198 | "idnum": 47, 199 | "creation_date": "2018-05-11T19:09:10.200728", 200 | "english_ability": "medium", 201 | "age": "35-44", 202 | "worked_in_research": false, 203 | "worked_in_NLP": false, 204 | "agreed_to_terms_and_conditions": true 205 | }, 206 | "user-10": { 207 | "english_ability": "native", 208 | "otherlangs": "none", 209 | "age": "55-64", 210 | "idnum": 10, 211 | "creation_date": "2018-04-27T13:12:00.631492", 212 | "french_ability": "poor", 213 | "gender": "male", 214 | "worked_in_research": false, 215 | "worked_in_NLP": false, 216 | "agreed_to_terms_and_conditions": true 217 | }, 218 | "user-51": { 219 | "french_ability": "poor", 220 | "gender": "female", 221 | "english_ability": "native", 222 | "otherlangs": "none", 223 | "creation_date": "2018-05-14T18:37:04.825042", 224 | "idnum": 51, 225 | "age": "55-64", 226 | "worked_in_research": false, 227 | "worked_in_NLP": false, 228 | "agreed_to_terms_and_conditions": true 229 | }, 230 | "user-26": { 231 | "french_ability": "native", 232 | "gender": "female", 233 | "otherlangs": "", 234 | "english_ability": "medium", 235 | "creation_date": "2018-05-02T19:40:23.480969", 236 | "idnum": 26, 237 | "age": "25-34", 238 | "worked_in_research": false, 239 | "worked_in_NLP": false, 240 | "agreed_to_terms_and_conditions": true 241 | }, 242 | "user-71": { 243 | "english_ability": "native", 244 | "otherlangs": "spanish, catalan, norwegian, russian, (portuguese, swedish)", 245 | "age": "25-34", 246 | "idnum": 71, 247 | "creation_date": "2018-05-17T12:41:23.875835", 248 | "french_ability": "medium", 249 | "gender": "male", 250 | "worked_in_research": true, 251 | "worked_in_NLP": true, 252 | "agreed_to_terms_and_conditions": true 253 | }, 254 | "user-67": { 255 | "age": "25-34", 256 | "idnum": 67, 257 | "gender": "female", 258 | "creation_date": "2018-05-17T18:34:28.910854", 259 | "english_ability": "good", 260 | "otherlangs": "", 261 | "french_ability": "native", 262 | "worked_in_research": false, 263 | "worked_in_NLP": false, 264 | "agreed_to_terms_and_conditions": true 265 | }, 266 | "user-30": { 267 | "age": "45-54", 268 | "idnum": 30, 269 | "gender": "female", 270 | "creation_date": "2018-05-03T12:00:44.072467", 271 | "english_ability": "medium", 272 | "otherlangs": "", 273 | "french_ability": "native", 274 | "worked_in_research": true, 275 | "worked_in_NLP": true, 276 | "agreed_to_terms_and_conditions": true 277 | }, 278 | "user-31": { 279 | "age": "55-64", 280 | "gender": "male", 281 | "idnum": 31, 282 | "otherlangs": "none", 283 | "creation_date": "2018-05-01T15:05:04.396938", 284 | "french_ability": "poor", 285 | "english_ability": "native", 286 | "worked_in_research": true, 287 | "worked_in_NLP": false, 288 | "agreed_to_terms_and_conditions": true 289 | }, 290 | "user-66": { 291 | "age": "18-24", 292 | "idnum": 66, 293 | "gender": "female", 294 | "creation_date": "2018-05-14T20:13:45.174188", 295 | "english_ability": "near-native", 296 | "otherlangs": "german", 297 | "french_ability": "native", 298 | "worked_in_research": false, 299 | "worked_in_NLP": false, 300 | "agreed_to_terms_and_conditions": true 301 | }, 302 | "user-70": { 303 | "gender": "male", 304 | "english_ability": "good", 305 | "otherlangs": "spanish", 306 | "age": "45-54", 307 | "idnum": 70, 308 | "creation_date": "2018-05-18T13:24:01.586193", 309 | "french_ability": "native", 310 | "worked_in_research": false, 311 | "worked_in_NLP": false, 312 | "agreed_to_terms_and_conditions": true 313 | }, 314 | "user-27": { 315 | "idnum": 27, 316 | "english_ability": "good", 317 | "age": "25-34", 318 | "gender": "male", 319 | "french_ability": "native", 320 | "otherlangs": "german/allemand", 321 | "creation_date": "2018-04-27T21:56:16.066322", 322 | "worked_in_research": false, 323 | "worked_in_NLP": true, 324 | "agreed_to_terms_and_conditions": true 325 | }, 326 | "user-1": { 327 | "english_ability": "near-native", 328 | "otherlangs": "german, slovak", 329 | "age": "35-44", 330 | "idnum": 1, 331 | "creation_date": "2018-04-24T13:34:36.142332", 332 | "french_ability": "native", 333 | "gender": "male", 334 | "worked_in_research": true, 335 | "worked_in_NLP": true, 336 | "agreed_to_terms_and_conditions": true 337 | }, 338 | "user-50": { 339 | "french_ability": "native", 340 | "gender": "male", 341 | "english_ability": "good", 342 | "otherlangs": "allemand", 343 | "creation_date": "2018-05-14T13:20:08.369903", 344 | "idnum": 50, 345 | "age": "45-54", 346 | "worked_in_research": true, 347 | "worked_in_NLP": true, 348 | "agreed_to_terms_and_conditions": true 349 | }, 350 | "user-11": { 351 | "otherlangs": "", 352 | "gender": "female", 353 | "age": "25-34", 354 | "creation_date": "2018-04-29T12:47:58.686184", 355 | "idnum": 11, 356 | "english_ability": "native", 357 | "french_ability": "poor", 358 | "worked_in_research": false, 359 | "worked_in_NLP": false, 360 | "agreed_to_terms_and_conditions": true 361 | }, 362 | "user-46": { 363 | "french_ability": "native", 364 | "gender": "male", 365 | "otherlangs": "", 366 | "idnum": 46, 367 | "creation_date": "2018-05-01T21:40:54.354017", 368 | "english_ability": "good", 369 | "age": "35-44", 370 | "worked_in_research": false, 371 | "worked_in_NLP": false, 372 | "agreed_to_terms_and_conditions": true 373 | }, 374 | "user-69": { 375 | "age": "35-44", 376 | "idnum": 69, 377 | "gender": "male", 378 | "creation_date": "2018-05-16T15:27:48.255858", 379 | "english_ability": "medium", 380 | "otherlangs": "", 381 | "french_ability": "native", 382 | "worked_in_research": true, 383 | "worked_in_NLP": true, 384 | "agreed_to_terms_and_conditions": true 385 | }, 386 | "user-2": { 387 | "english_ability": "native", 388 | "otherlangs": "", 389 | "age": "55-64", 390 | "idnum": 2, 391 | "french_ability": "medium", 392 | "creation_date": "2018-04-25T09:34:50.357566", 393 | "gender": "female", 394 | "worked_in_research": false, 395 | "worked_in_NLP": false, 396 | "agreed_to_terms_and_conditions": true 397 | }, 398 | "user-28": { 399 | "idnum": 28, 400 | "french_ability": "poor", 401 | "age": "25-34", 402 | "gender": "male", 403 | "english_ability": "native", 404 | "otherlangs": "", 405 | "creation_date": "2018-04-30T16:38:02.633151", 406 | "worked_in_research": false, 407 | "worked_in_NLP": false, 408 | "agreed_to_terms_and_conditions": true 409 | }, 410 | "user-53": { 411 | "french_ability": "none", 412 | "gender": "female", 413 | "otherlangs": "", 414 | "idnum": 53, 415 | "creation_date": "2018-05-14T17:45:02.506705", 416 | "english_ability": "native", 417 | "age": "55-64", 418 | "worked_in_research": false, 419 | "worked_in_NLP": false, 420 | "agreed_to_terms_and_conditions": true 421 | }, 422 | "user-12": { 423 | "french_ability": "native", 424 | "english_ability": "good", 425 | "otherlangs": "allemand", 426 | "gender": "male", 427 | "age": "35-44", 428 | "idnum": 12, 429 | "creation_date": "2018-04-27T21:50:58.298417", 430 | "worked_in_research": false, 431 | "worked_in_NLP": false, 432 | "agreed_to_terms_and_conditions": true 433 | }, 434 | "user-45": { 435 | "gender": "female", 436 | "english_ability": "good", 437 | "otherlangs": "none", 438 | "age": "65-74", 439 | "idnum": 45, 440 | "creation_date": "2018-05-09T19:59:53.841263", 441 | "french_ability": "none", 442 | "worked_in_research": false, 443 | "worked_in_NLP": false, 444 | "agreed_to_terms_and_conditions": true 445 | }, 446 | "user-32": { 447 | "age": "45-54", 448 | "gender": "male", 449 | "idnum": 32, 450 | "otherlangs": "spanish, italian", 451 | "creation_date": "2018-05-03T13:54:36.656129", 452 | "french_ability": "native", 453 | "english_ability": "good", 454 | "worked_in_research": false, 455 | "worked_in_NLP": false, 456 | "agreed_to_terms_and_conditions": true 457 | }, 458 | "user-65": { 459 | "english_ability": "native", 460 | "otherlangs": "spanish", 461 | "age": "25-34", 462 | "idnum": 65, 463 | "creation_date": "2018-05-17T18:58:33.952804", 464 | "french_ability": "near-native", 465 | "gender": "male", 466 | "worked_in_research": false, 467 | "worked_in_NLP": false, 468 | "agreed_to_terms_and_conditions": true 469 | }, 470 | "user-73": { 471 | "gender": "male", 472 | "english_ability": "good", 473 | "otherlangs": "", 474 | "age": "25-34", 475 | "idnum": 73, 476 | "creation_date": "2018-05-18T16:54:38.039162", 477 | "french_ability": "native", 478 | "worked_in_research": true, 479 | "worked_in_NLP": false, 480 | "agreed_to_terms_and_conditions": true 481 | }, 482 | "user-24": { 483 | "gender": "female", 484 | "english_ability": "native", 485 | "otherlangs": "", 486 | "age": "55-64", 487 | "idnum": 24, 488 | "creation_date": "2018-04-30T11:12:05.976575", 489 | "french_ability": "poor", 490 | "worked_in_research": false, 491 | "worked_in_NLP": false, 492 | "agreed_to_terms_and_conditions": true 493 | }, 494 | "user-49": { 495 | "english_ability": "near-native", 496 | "otherlangs": "", 497 | "age": "65-74", 498 | "idnum": 49, 499 | "gender": "male", 500 | "creation_date": "2018-05-12T19:11:54.301318", 501 | "french_ability": "poor", 502 | "worked_in_research": false, 503 | "worked_in_NLP": false, 504 | "agreed_to_terms_and_conditions": true 505 | }, 506 | "user-48": { 507 | "french_ability": "medium", 508 | "gender": "female", 509 | "english_ability": "native", 510 | "otherlangs": "", 511 | "creation_date": "2018-05-04T16:55:29.021776", 512 | "idnum": 48, 513 | "age": "55-64", 514 | "worked_in_research": false, 515 | "worked_in_NLP": false, 516 | "agreed_to_terms_and_conditions": true 517 | }, 518 | "user-25": { 519 | "idnum": 25, 520 | "french_ability": "native", 521 | "age": "25-34", 522 | "gender": "male", 523 | "english_ability": "good", 524 | "otherlangs": "", 525 | "creation_date": "2018-05-02T19:30:10.455938", 526 | "worked_in_research": false, 527 | "worked_in_NLP": false, 528 | "agreed_to_terms_and_conditions": true 529 | }, 530 | "user-72": { 531 | "gender": "male", 532 | "english_ability": "medium", 533 | "otherlangs": "", 534 | "age": "25-34", 535 | "idnum": 72, 536 | "creation_date": "2018-05-18T16:05:45.910456", 537 | "french_ability": "native", 538 | "worked_in_research": false, 539 | "worked_in_NLP": false, 540 | "agreed_to_terms_and_conditions": true 541 | }, 542 | "user-64": { 543 | "english_ability": "near-native", 544 | "otherlangs": "russian, spanish", 545 | "age": "25-34", 546 | "idnum": 64, 547 | "creation_date": "2018-05-17T17:15:07.264806", 548 | "french_ability": "native", 549 | "gender": "female", 550 | "worked_in_research": false, 551 | "worked_in_NLP": false, 552 | "agreed_to_terms_and_conditions": true 553 | }, 554 | "user-33": { 555 | "age": "65-74", 556 | "gender": "male", 557 | "idnum": 33, 558 | "otherlangs": "", 559 | "creation_date": "2018-05-03T13:15:51.206957", 560 | "french_ability": "poor", 561 | "english_ability": "native", 562 | "worked_in_research": false, 563 | "worked_in_NLP": false, 564 | "agreed_to_terms_and_conditions": true 565 | }, 566 | "user-44": { 567 | "age": "25-34", 568 | "gender": "male", 569 | "idnum": 44, 570 | "otherlangs": "", 571 | "creation_date": "2018-05-09T18:22:11.735377", 572 | "french_ability": "medium", 573 | "english_ability": "native", 574 | "worked_in_research": false, 575 | "worked_in_NLP": false, 576 | "agreed_to_terms_and_conditions": true 577 | }, 578 | "user-13": { 579 | "otherlangs": "dutch", 580 | "gender": "female", 581 | "age": "25-34", 582 | "creation_date": "2018-04-29T15:25:19.699471", 583 | "idnum": 13, 584 | "english_ability": "good", 585 | "french_ability": "native", 586 | "worked_in_research": false, 587 | "worked_in_NLP": false, 588 | "agreed_to_terms_and_conditions": true 589 | }, 590 | "user-52": { 591 | "french_ability": "poor", 592 | "gender": "female", 593 | "english_ability": "native", 594 | "otherlangs": "none", 595 | "creation_date": "2018-05-14T18:38:29.372010", 596 | "idnum": 52, 597 | "age": "45-54", 598 | "worked_in_research": false, 599 | "worked_in_NLP": false, 600 | "agreed_to_terms_and_conditions": true 601 | }, 602 | "user-29": { 603 | "age": "65-74", 604 | "gender": "male", 605 | "idnum": 29, 606 | "otherlangs": "none", 607 | "creation_date": "2018-05-01T06:34:59.055115", 608 | "french_ability": "poor", 609 | "english_ability": "native", 610 | "worked_in_research": false, 611 | "worked_in_NLP": false, 612 | "agreed_to_terms_and_conditions": true 613 | }, 614 | "user-68": { 615 | "age": "25-34", 616 | "idnum": 68, 617 | "gender": "male", 618 | "creation_date": "2018-05-18T08:17:32.624100", 619 | "english_ability": "good", 620 | "otherlangs": "", 621 | "french_ability": "native", 622 | "worked_in_research": true, 623 | "worked_in_NLP": false, 624 | "agreed_to_terms_and_conditions": true 625 | }, 626 | "user-3": { 627 | "english_ability": "native", 628 | "otherlangs": "", 629 | "age": "25-34", 630 | "idnum": 3, 631 | "creation_date": "2018-04-25T09:46:50.458906", 632 | "french_ability": "near-native", 633 | "gender": "female", 634 | "worked_in_research": true, 635 | "worked_in_NLP": true, 636 | "agreed_to_terms_and_conditions": true 637 | }, 638 | "user-34": { 639 | "age": "45-54", 640 | "idnum": 34, 641 | "gender": "male", 642 | "creation_date": "2018-05-04T16:09:58.277387", 643 | "english_ability": "native", 644 | "otherlangs": "", 645 | "french_ability": "none", 646 | "worked_in_research": false, 647 | "worked_in_NLP": false, 648 | "agreed_to_terms_and_conditions": true 649 | }, 650 | "user-63": { 651 | "age": "25-34", 652 | "idnum": 63, 653 | "gender": "male", 654 | "creation_date": "2018-05-17T10:00:08.411214", 655 | "english_ability": "native", 656 | "otherlangs": "dutch", 657 | "french_ability": "none", 658 | "worked_in_research": true, 659 | "worked_in_NLP": true, 660 | "agreed_to_terms_and_conditions": true 661 | }, 662 | "user-8": { 663 | "gender": "female", 664 | "otherlangs": "", 665 | "english_ability": "good", 666 | "idnum": 8, 667 | "french_ability": "native", 668 | "age": "25-34", 669 | "creation_date": "2018-04-27T13:26:32.153820", 670 | "worked_in_research": true, 671 | "worked_in_NLP": false, 672 | "agreed_to_terms_and_conditions": true 673 | }, 674 | "user-75": { 675 | "gender": "female", 676 | "english_ability": "native", 677 | "otherlangs": "", 678 | "age": "55-64", 679 | "idnum": 75, 680 | "creation_date": "2018-05-21T18:08:52.358225", 681 | "french_ability": "native", 682 | "worked_in_research": false, 683 | "worked_in_NLP": false, 684 | "agreed_to_terms_and_conditions": true 685 | }, 686 | "user-22": { 687 | "idnum": 22, 688 | "french_ability": "native", 689 | "age": "25-34", 690 | "gender": "male", 691 | "english_ability": "good", 692 | "otherlangs": "", 693 | "creation_date": "2018-04-29T11:55:09.656535", 694 | "worked_in_research": true, 695 | "worked_in_NLP": true, 696 | "agreed_to_terms_and_conditions": true 697 | }, 698 | "user-59": { 699 | "age": "35-44", 700 | "idnum": 59, 701 | "gender": "female", 702 | "creation_date": "2018-05-17T10:11:46.659337", 703 | "english_ability": "native", 704 | "otherlangs": "german", 705 | "french_ability": "medium", 706 | "worked_in_research": true, 707 | "worked_in_NLP": true, 708 | "agreed_to_terms_and_conditions": true 709 | }, 710 | "user-18": { 711 | "french_ability": "good", 712 | "gender": "male", 713 | "english_ability": "native", 714 | "otherlangs": "spanish", 715 | "creation_date": "2018-04-27T20:09:24.216476", 716 | "idnum": 18, 717 | "age": "55-64", 718 | "worked_in_research": true, 719 | "worked_in_NLP": true, 720 | "agreed_to_terms_and_conditions": true 721 | }, 722 | "user-38": { 723 | "age": "65-74", 724 | "gender": "female", 725 | "idnum": 38, 726 | "otherlangs": "german", 727 | "creation_date": "2018-05-07T19:12:09.913326", 728 | "french_ability": "medium", 729 | "english_ability": "native", 730 | "worked_in_research": false, 731 | "worked_in_NLP": false, 732 | "agreed_to_terms_and_conditions": true 733 | }, 734 | "user-4": { 735 | "age": "35-44", 736 | "idnum": 4, 737 | "gender": "female", 738 | "creation_date": "2018-04-26T20:09:50.034718", 739 | "english_ability": "near-native", 740 | "otherlangs": "german", 741 | "french_ability": "native", 742 | "worked_in_research": true, 743 | "worked_in_NLP": true, 744 | "agreed_to_terms_and_conditions": true 745 | }, 746 | "user-55": { 747 | "english_ability": "good", 748 | "otherlangs": "", 749 | "age": "25-34", 750 | "idnum": 55, 751 | "creation_date": "2018-05-15T18:09:16.668712", 752 | "french_ability": "native", 753 | "gender": "female", 754 | "worked_in_research": false, 755 | "worked_in_NLP": false, 756 | "agreed_to_terms_and_conditions": true 757 | }, 758 | "user-14": { 759 | "english_ability": "good", 760 | "otherlangs": "", 761 | "age": "18-24", 762 | "idnum": 14, 763 | "french_ability": "native", 764 | "creation_date": "2018-04-26T13:27:11.416655", 765 | "gender": "female", 766 | "worked_in_research": true, 767 | "worked_in_NLP": true, 768 | "agreed_to_terms_and_conditions": true 769 | }, 770 | "user-43": { 771 | "age": "65-74", 772 | "idnum": 43, 773 | "gender": "male", 774 | "creation_date": "2018-05-08T18:52:41.506093", 775 | "english_ability": "good", 776 | "otherlangs": "", 777 | "french_ability": "native", 778 | "worked_in_research": true, 779 | "worked_in_NLP": false, 780 | "agreed_to_terms_and_conditions": true 781 | }, 782 | "user-42": { 783 | "age": "55-64", 784 | "gender": "female", 785 | "idnum": 42, 786 | "otherlangs": "spanish", 787 | "creation_date": "2018-05-08T18:34:17.964134", 788 | "french_ability": "medium", 789 | "english_ability": "native", 790 | "worked_in_research": false, 791 | "worked_in_NLP": false, 792 | "agreed_to_terms_and_conditions": true 793 | }, 794 | "user-15": { 795 | "english_ability": "good", 796 | "otherlangs": "spanish", 797 | "age": "25-34", 798 | "idnum": 15, 799 | "creation_date": "2018-04-30T09:23:28.281142", 800 | "french_ability": "native", 801 | "gender": "male", 802 | "worked_in_research": true, 803 | "worked_in_NLP": true, 804 | "agreed_to_terms_and_conditions": true 805 | }, 806 | "user-54": { 807 | "age": "25-34", 808 | "idnum": 54, 809 | "gender": "female", 810 | "creation_date": "2018-05-15T12:59:42.603597", 811 | "english_ability": "medium", 812 | "otherlangs": "", 813 | "french_ability": "native", 814 | "worked_in_research": false, 815 | "worked_in_NLP": false, 816 | "agreed_to_terms_and_conditions": true 817 | }, 818 | "user-5": { 819 | "gender": "male", 820 | "idnum": 5, 821 | "age": "55-64", 822 | "creation_date": "2018-04-26T20:43:07.578120", 823 | "french_ability": "good", 824 | "otherlangs": "german, estonian", 825 | "english_ability": "native", 826 | "worked_in_research": true, 827 | "worked_in_NLP": true, 828 | "agreed_to_terms_and_conditions": true 829 | }, 830 | "user-39": { 831 | "age": "55-64", 832 | "gender": "female", 833 | "idnum": 39, 834 | "otherlangs": "", 835 | "creation_date": "2018-05-08T12:44:39.770276", 836 | "french_ability": "native", 837 | "english_ability": "medium", 838 | "worked_in_research": false, 839 | "worked_in_NLP": false, 840 | "agreed_to_terms_and_conditions": true 841 | }, 842 | "user-19": { 843 | "french_ability": "native", 844 | "age": "45-54", 845 | "gender": "female", 846 | "english_ability": "poor", 847 | "otherlangs": "", 848 | "creation_date": "2018-04-30T17:03:23.475142", 849 | "idnum": 19, 850 | "worked_in_research": false, 851 | "worked_in_NLP": false, 852 | "agreed_to_terms_and_conditions": true 853 | }, 854 | "user-58": { 855 | "age": "25-34", 856 | "idnum": 58, 857 | "gender": "male", 858 | "creation_date": "2018-05-17T10:46:28.639646", 859 | "english_ability": "good", 860 | "otherlangs": "", 861 | "french_ability": "native", 862 | "worked_in_research": true, 863 | "worked_in_NLP": true, 864 | "agreed_to_terms_and_conditions": true 865 | }, 866 | "user-23": { 867 | "age": "25-34", 868 | "idnum": 23, 869 | "gender": "male", 870 | "creation_date": "2018-04-29T12:30:25.985724", 871 | "english_ability": "native", 872 | "otherlangs": "", 873 | "french_ability": "poor", 874 | "worked_in_research": false, 875 | "worked_in_NLP": false, 876 | "agreed_to_terms_and_conditions": true 877 | }, 878 | "user-74": { 879 | "english_ability": "native", 880 | "otherlangs": "", 881 | "age": "18-24", 882 | "idnum": 74, 883 | "creation_date": "2018-05-08T18:59:02.753243", 884 | "french_ability": "native", 885 | "gender": "female", 886 | "worked_in_research": false, 887 | "worked_in_NLP": false, 888 | "agreed_to_terms_and_conditions": true 889 | }, 890 | "user-62": { 891 | "english_ability": "medium", 892 | "otherlangs": "", 893 | "age": "25-34", 894 | "idnum": 62, 895 | "creation_date": "2018-05-17T10:07:59.208971", 896 | "french_ability": "native", 897 | "gender": "female", 898 | "worked_in_research": false, 899 | "worked_in_NLP": false, 900 | "agreed_to_terms_and_conditions": true 901 | }, 902 | "user-9": { 903 | "french_ability": "poor", 904 | "gender": "female", 905 | "idnum": 9, 906 | "english_ability": "native", 907 | "age": "25-34", 908 | "creation_date": "2018-04-28T07:36:20.122686", 909 | "otherlangs": "", 910 | "worked_in_research": false, 911 | "worked_in_NLP": false, 912 | "agreed_to_terms_and_conditions": true 913 | }, 914 | "user-35": { 915 | "french_ability": "native", 916 | "gender": "male", 917 | "english_ability": "medium", 918 | "otherlangs": "", 919 | "creation_date": "2018-05-04T19:19:49.702669", 920 | "idnum": 35, 921 | "age": "35-44", 922 | "worked_in_research": false, 923 | "worked_in_NLP": false, 924 | "agreed_to_terms_and_conditions": true 925 | } 926 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/dialogues/2018-05-04T19-18-57.178971_french_english_16_3.json: -------------------------------------------------------------------------------- 1 | { 2 | "start_time": "2018-05-04T19:18:57.178971", 3 | "end_time": null, 4 | "scenario": [ 5 | [ 6 | "You are at home in the evening.", 7 | "Vous \u00eates \u00e0 la maison le soir." 8 | ], 9 | [ 10 | "You are telling your spouse about the awful day you had.", 11 | "Vous racontez \u00e0 votre partenaire la journ\u00e9e difficile que vous venez de passer." 12 | ], 13 | [ 14 | "You are listening to your spouse telling you about the awful day they had.", 15 | "Vous \u00e9coutez votre partenaire qui vous raconte la journ\u00e9e difficile qu'il/elle vient de passer." 16 | ] 17 | ], 18 | "user1": { 19 | "turn_number": 2, 20 | "initiated_dialogue": true, 21 | "role_num": 1, 22 | "role": [ 23 | "You are telling your spouse about the awful day you had.", 24 | "Vous racontez \u00e0 votre partenaire la journ\u00e9e difficile que vous venez de passer." 25 | ], 26 | "lang": "french", 27 | "eval-stage": false, 28 | "useragent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36" 29 | }, 30 | "user2": { 31 | "turn_number": 1, 32 | "initiated_dialogue": false, 33 | "useragent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/11.1 Safari/605.1.15", 34 | "role": [ 35 | "You are listening to your spouse telling you about the awful day they had.", 36 | "Vous \u00e9coutez votre partenaire qui vous raconte la journ\u00e9e difficile qu'il/elle vient de passer." 37 | ], 38 | "lang": "english", 39 | "eval-stage": true, 40 | "rolenum": 2 41 | }, 42 | "translation_model": "2to2", 43 | "utterances": { 44 | "0": { 45 | "language": "english", 46 | "original_text": "Shall I make you a hot chocolate?", 47 | "preprocessed_text": " shall I make you a hot chocolate ?", 48 | "translated_text": "sant\u00e9 je te pr\u00e9pare un chocolat chaud ?", 49 | "postprocessed_text": "Je te pr\u00e9pare un chocolat chaud ?", 50 | "composition_time": "2018-05-04T19:19:49.406087", 51 | "preprocessing_begin": "2018-05-04T19:19:49.453604", 52 | "preprocessing_end": "2018-05-04T19:19:51.636673", 53 | "translation_begin": "2018-05-04T19:19:51.636858", 54 | "translation_end": "2018-05-04T19:19:53.775051", 55 | "postprocessing_begin": "2018-05-04T19:19:53.775411", 56 | "postprocessing_end": "2018-05-04T19:19:53.826053", 57 | "sent_time": "2018-05-04T19:19:53.826980", 58 | "eval": { 59 | "problem_history": [], 60 | "verbatim_history": [], 61 | "verbatim": "", 62 | "judgment_history": [ 63 | [ 64 | "perfect", 65 | "2018-05-04T19:22:24.637998" 66 | ] 67 | ], 68 | "judgment": "perfect", 69 | "problems": [] 70 | }, 71 | "reference_translation": "Je te fais un chocolat chaud\u00a0?", 72 | "normalised_version": "" 73 | }, 74 | "1": { 75 | "language": "english", 76 | "original_text": "Everything will seem better after a nice warm drink.", 77 | "preprocessed_text": "shall I make you a hot chocolate ? everything will seem better after a nice warm drink .", 78 | "translated_text": "je te pr\u00e9pare un chocolat chaud ? tout ira mieux apr\u00e8s une bonne boisson chaude .", 79 | "postprocessed_text": "Tout ira mieux apr\u00e8s une bonne boisson chaude.", 80 | "composition_time": "2018-05-04T19:19:49.406087", 81 | "preprocessing_begin": "2018-05-04T19:19:49.453604", 82 | "preprocessing_end": "2018-05-04T19:19:51.636673", 83 | "translation_begin": "2018-05-04T19:19:51.636858", 84 | "translation_end": "2018-05-04T19:19:53.775051", 85 | "postprocessing_begin": "2018-05-04T19:19:53.775411", 86 | "postprocessing_end": "2018-05-04T19:19:53.826053", 87 | "sent_time": "2018-05-04T19:19:53.827399", 88 | "eval": { 89 | "problem_history": [], 90 | "verbatim_history": [], 91 | "verbatim": "", 92 | "judgment_history": [ 93 | [ 94 | "perfect", 95 | "2018-05-04T19:22:26.115590" 96 | ] 97 | ], 98 | "judgment": "perfect", 99 | "problems": [] 100 | }, 101 | "reference_translation": "Tout ira mieux apr\u00e8s une bonne boisson chaude.", 102 | "normalised_version": "" 103 | }, 104 | "2": { 105 | "language": "french", 106 | "original_text": "C'est gentil mais je pr\u00e9f\u00e8re un caf\u00e9.", 107 | "preprocessed_text": "tout ira mieux apr\u00e8s une bonne boisson chaude . c' est gentil mais je pr\u00e9f\u00e8re un caf\u00e9 .", 108 | "translated_text": "everything will be fine after a nice warm drink . that 's sweet , but I prefer coffee .", 109 | "postprocessed_text": "That's sweet, but I prefer coffee.", 110 | "composition_time": "2018-05-04T19:22:18.437332", 111 | "preprocessing_begin": "2018-05-04T19:22:18.485351", 112 | "preprocessing_end": "2018-05-04T19:22:20.876450", 113 | "translation_begin": "2018-05-04T19:22:20.876608", 114 | "translation_end": "2018-05-04T19:22:24.595425", 115 | "postprocessing_begin": "2018-05-04T19:22:24.595873", 116 | "postprocessing_end": "2018-05-04T19:22:24.629989", 117 | "sent_time": "2018-05-04T19:22:24.631592", 118 | "eval": { 119 | "problem_history": [], 120 | "verbatim_history": [], 121 | "verbatim": "", 122 | "judgment_history": [ 123 | [ 124 | "perfect", 125 | "2018-05-04T19:22:32.609460" 126 | ] 127 | ], 128 | "judgment": "perfect", 129 | "problems": [] 130 | }, 131 | "reference_translation": "That\u2019s nice of you but I\u2019d prefer a coffee.", 132 | "normalised_version": "" 133 | }, 134 | "3": { 135 | "language": "french", 136 | "original_text": "Avec du sucre Mais l'id\u00e9al serait une caipirinha...!", 137 | "preprocessed_text": "c' est gentil mais je pr\u00e9f\u00e8re un caf\u00e9 . avec du sucre Mais l' id\u00e9al serait une c@@ ai@@ pir@@ inha ... !", 138 | "translated_text": "that 's sweet , but I prefer coffee . with sugar but the ideal would be a c@@ ai@@ pir@@ inha ... !", 139 | "postprocessed_text": "With sugar but the ideal would be a caipirinha...!", 140 | "composition_time": "2018-05-04T19:22:18.437332", 141 | "preprocessing_begin": "2018-05-04T19:22:18.485351", 142 | "preprocessing_end": "2018-05-04T19:22:20.876450", 143 | "translation_begin": "2018-05-04T19:22:20.876608", 144 | "translation_end": "2018-05-04T19:22:24.595425", 145 | "postprocessing_begin": "2018-05-04T19:22:24.595873", 146 | "postprocessing_end": "2018-05-04T19:22:24.629989", 147 | "sent_time": "2018-05-04T19:22:24.632414", 148 | "eval": { 149 | "problem_history": [], 150 | "verbatim_history": [], 151 | "verbatim": "", 152 | "judgment_history": [ 153 | [ 154 | "perfect", 155 | "2018-05-04T19:22:33.176155" 156 | ] 157 | ], 158 | "judgment": "perfect", 159 | "problems": [] 160 | }, 161 | "reference_translation": "With sugar. But ideally I\u2019d like a caipirinha!", 162 | "normalised_version": "Avec du sucre. Mais l'id\u00e9al serait une caipirinha!" 163 | }, 164 | "4": { 165 | "language": "english", 166 | "original_text": "Oh dear!", 167 | "preprocessed_text": "with sugar but the ideal would be a c@@ ai@@ pir@@ inha ... ! oh dear !", 168 | "translated_text": "avec du sucre , mais l' id\u00e9al serait un c@@ ai@@ pir@@ inha ... ! oh mon Dieu !", 169 | "postprocessed_text": "Oh mon Dieu !", 170 | "composition_time": "2018-05-04T19:23:27.922018", 171 | "preprocessing_begin": "2018-05-04T19:23:27.964710", 172 | "preprocessing_end": "2018-05-04T19:23:30.060576", 173 | "translation_begin": "2018-05-04T19:23:30.060665", 174 | "translation_end": "2018-05-04T19:23:36.916796", 175 | "postprocessing_begin": "2018-05-04T19:23:36.917195", 176 | "postprocessing_end": "2018-05-04T19:23:36.962475", 177 | "sent_time": "2018-05-04T19:23:36.963323", 178 | "eval": { 179 | "problem_history": [], 180 | "verbatim_history": [], 181 | "verbatim": "", 182 | "judgment_history": [ 183 | [ 184 | "perfect", 185 | "2018-05-04T19:23:53.947444" 186 | ] 187 | ], 188 | "judgment": "perfect", 189 | "problems": [] 190 | }, 191 | "reference_translation": "Mon Dieu\u00a0!", 192 | "normalised_version": "" 193 | }, 194 | "5": { 195 | "language": "english", 196 | "original_text": "It must have been a really tough day.", 197 | "preprocessed_text": "oh dear ! it must have been a really tough day .", 198 | "translated_text": "oh mon Dieu ! \u00e7a a d\u00fb \u00eatre une dure journ\u00e9e .", 199 | "postprocessed_text": "\u00c7a a d\u00fb \u00eatre une dure journ\u00e9e.", 200 | "composition_time": "2018-05-04T19:23:27.922018", 201 | "preprocessing_begin": "2018-05-04T19:23:27.964710", 202 | "preprocessing_end": "2018-05-04T19:23:30.060576", 203 | "translation_begin": "2018-05-04T19:23:30.060665", 204 | "translation_end": "2018-05-04T19:23:36.916796", 205 | "postprocessing_begin": "2018-05-04T19:23:36.917195", 206 | "postprocessing_end": "2018-05-04T19:23:36.962475", 207 | "sent_time": "2018-05-04T19:23:36.963709", 208 | "eval": { 209 | "problem_history": [], 210 | "verbatim_history": [], 211 | "verbatim": "", 212 | "judgment_history": [ 213 | [ 214 | "perfect", 215 | "2018-05-04T19:23:55.495529" 216 | ] 217 | ], 218 | "judgment": "perfect", 219 | "problems": [] 220 | }, 221 | "reference_translation": "Tu as d\u00fb passer une journ\u00e9e bien difficile.", 222 | "normalised_version": "" 223 | }, 224 | "6": { 225 | "language": "english", 226 | "original_text": "Would you like to talk about it?", 227 | "preprocessed_text": "it must have been a really tough day . would you like to talk about it ?", 228 | "translated_text": "\u00e7a a d\u00fb \u00eatre une dure journ\u00e9e . tu veux en parler ?", 229 | "postprocessed_text": "Tu veux en parler ?", 230 | "composition_time": "2018-05-04T19:23:27.922018", 231 | "preprocessing_begin": "2018-05-04T19:23:27.964710", 232 | "preprocessing_end": "2018-05-04T19:23:30.060576", 233 | "translation_begin": "2018-05-04T19:23:30.060665", 234 | "translation_end": "2018-05-04T19:23:36.916796", 235 | "postprocessing_begin": "2018-05-04T19:23:36.917195", 236 | "postprocessing_end": "2018-05-04T19:23:36.962475", 237 | "sent_time": "2018-05-04T19:23:36.964120", 238 | "eval": { 239 | "problem_history": [], 240 | "verbatim_history": [], 241 | "verbatim": "", 242 | "judgment_history": [ 243 | [ 244 | "perfect", 245 | "2018-05-04T19:23:57.993710" 246 | ] 247 | ], 248 | "judgment": "perfect", 249 | "problems": [] 250 | }, 251 | "reference_translation": "Tu veux en discuter\u00a0?", 252 | "normalised_version": "" 253 | }, 254 | "7": { 255 | "language": "english", 256 | "original_text": "What went on at work in the end?", 257 | "preprocessed_text": "would you like to talk about it ? what went on at work in the end ?", 258 | "translated_text": "vous voulez en parler ? qu' est @-@ ce qui s' est pass\u00e9 \u00e0 la fin ?", 259 | "postprocessed_text": "Qu'est-ce qui s'est pass\u00e9 \u00e0 la fin ?", 260 | "composition_time": "2018-05-04T19:23:27.922018", 261 | "preprocessing_begin": "2018-05-04T19:23:27.964710", 262 | "preprocessing_end": "2018-05-04T19:23:30.060576", 263 | "translation_begin": "2018-05-04T19:23:30.060665", 264 | "translation_end": "2018-05-04T19:23:36.916796", 265 | "postprocessing_begin": "2018-05-04T19:23:36.917195", 266 | "postprocessing_end": "2018-05-04T19:23:36.962475", 267 | "sent_time": "2018-05-04T19:23:36.964498", 268 | "eval": { 269 | "problem_history": [], 270 | "verbatim_history": [], 271 | "verbatim": "", 272 | "judgment_history": [ 273 | [ 274 | "perfect", 275 | "2018-05-04T19:24:00.034450" 276 | ] 277 | ], 278 | "judgment": "perfect", 279 | "problems": [] 280 | }, 281 | "reference_translation": "Qu'est-ce qui s'est pass\u00e9 au travail finalement\u00a0?", 282 | "normalised_version": "" 283 | }, 284 | "8": { 285 | "language": "english", 286 | "original_text": "Did you manage to meet the deadline?", 287 | "preprocessed_text": "what went on at work in the end ? did you manage to meet the deadline ?", 288 | "translated_text": "qu' est @-@ ce qui s' est pass\u00e9 au travail \u00e0 la fin ? as @-@ tu r\u00e9ussi \u00e0 rencontrer la date limite ?", 289 | "postprocessed_text": "As-tu r\u00e9ussi \u00e0 rencontrer la date limite ?", 290 | "composition_time": "2018-05-04T19:23:27.922018", 291 | "preprocessing_begin": "2018-05-04T19:23:27.964710", 292 | "preprocessing_end": "2018-05-04T19:23:30.060576", 293 | "translation_begin": "2018-05-04T19:23:30.060665", 294 | "translation_end": "2018-05-04T19:23:36.916796", 295 | "postprocessing_begin": "2018-05-04T19:23:36.917195", 296 | "postprocessing_end": "2018-05-04T19:23:36.962475", 297 | "sent_time": "2018-05-04T19:23:36.964946", 298 | "eval": { 299 | "problem_history": [ 300 | [ 301 | "meaning", 302 | "2018-05-04T19:24:06.367525", 303 | true 304 | ], 305 | [ 306 | "coherence", 307 | "2018-05-04T19:25:33.683207", 308 | true 309 | ] 310 | ], 311 | "verbatim_history": [], 312 | "verbatim": "", 313 | "judgment_history": [ 314 | [ 315 | "medium", 316 | "2018-05-04T19:24:03.784984" 317 | ] 318 | ], 319 | "judgment": "medium", 320 | "problems": [ 321 | "meaning", 322 | "coherence" 323 | ] 324 | }, 325 | "reference_translation": "Tu as r\u00e9ussi \u00e0 finir avant l'heure limite\u00a0?", 326 | "normalised_version": "" 327 | }, 328 | "9": { 329 | "language": "french", 330 | "original_text": "Oui, tr\u00e8s dure journ\u00e9e.", 331 | "preprocessed_text": "as @-@ tu r\u00e9ussi \u00e0 rencontrer la date limite ? oui , tr\u00e8s dure journ\u00e9e .", 332 | "translated_text": "did you manage to meet the deadline ? yes , very hard day .", 333 | "postprocessed_text": "Yes, very hard day.", 334 | "composition_time": "2018-05-04T19:25:39.308101", 335 | "preprocessing_begin": "2018-05-04T19:25:39.350163", 336 | "preprocessing_end": "2018-05-04T19:25:41.483448", 337 | "translation_begin": "2018-05-04T19:25:41.483554", 338 | "translation_end": "2018-05-04T19:25:44.591133", 339 | "postprocessing_begin": "2018-05-04T19:25:44.591720", 340 | "postprocessing_end": "2018-05-04T19:25:44.628627", 341 | "sent_time": "2018-05-04T19:25:44.630707", 342 | "eval": { 343 | "problem_history": [], 344 | "verbatim_history": [], 345 | "verbatim": "", 346 | "judgment_history": [ 347 | [ 348 | "perfect", 349 | "2018-05-04T19:25:58.546768" 350 | ] 351 | ], 352 | "judgment": "perfect", 353 | "problems": [] 354 | }, 355 | "reference_translation": "Yes, a very tough day.", 356 | "normalised_version": "" 357 | }, 358 | "10": { 359 | "language": "french", 360 | "original_text": "Nous avons perdu un contrat important et nous ne comprenons pas pourquoi.", 361 | "preprocessed_text": "oui , tr\u00e8s dure journ\u00e9e . nous avons perdu un contrat important et nous ne comprenons pas pourquoi .", 362 | "translated_text": "yes , very hard day . we have lost an important contract and we don 't understand why .", 363 | "postprocessed_text": "We have lost an important contract and we don't understand why.", 364 | "composition_time": "2018-05-04T19:25:39.308101", 365 | "preprocessing_begin": "2018-05-04T19:25:39.350163", 366 | "preprocessing_end": "2018-05-04T19:25:41.483448", 367 | "translation_begin": "2018-05-04T19:25:41.483554", 368 | "translation_end": "2018-05-04T19:25:44.591133", 369 | "postprocessing_begin": "2018-05-04T19:25:44.591720", 370 | "postprocessing_end": "2018-05-04T19:25:44.628627", 371 | "sent_time": "2018-05-04T19:25:44.632111", 372 | "eval": { 373 | "problem_history": [], 374 | "verbatim_history": [], 375 | "verbatim": "", 376 | "judgment_history": [ 377 | [ 378 | "perfect", 379 | "2018-05-04T19:26:16.624537" 380 | ] 381 | ], 382 | "judgment": "perfect", 383 | "problems": [] 384 | }, 385 | "reference_translation": "We lost an important contract and we don\u2019t know why.", 386 | "normalised_version": "" 387 | }, 388 | "11": { 389 | "language": "english", 390 | "original_text": "Did they not explain why?", 391 | "preprocessed_text": "we have lost an important contract and we don 't understand why . did they not explain why ?", 392 | "translated_text": "nous avons perdu un contrat important et nous ne comprenons pas pourquoi . ne vous ont @-@ ils pas expliqu\u00e9 pourquoi ?", 393 | "postprocessed_text": "Ne vous ont-ils pas expliqu\u00e9 pourquoi ?", 394 | "composition_time": "2018-05-04T19:26:11.608082", 395 | "preprocessing_begin": "2018-05-04T19:26:11.648443", 396 | "preprocessing_end": "2018-05-04T19:26:13.795119", 397 | "translation_begin": "2018-05-04T19:26:13.795172", 398 | "translation_end": "2018-05-04T19:26:16.581810", 399 | "postprocessing_begin": "2018-05-04T19:26:16.582195", 400 | "postprocessing_end": "2018-05-04T19:26:16.616627", 401 | "sent_time": "2018-05-04T19:26:16.618048", 402 | "eval": { 403 | "problem_history": [], 404 | "verbatim_history": [], 405 | "verbatim": "", 406 | "judgment_history": [ 407 | [ 408 | "perfect", 409 | "2018-05-04T19:26:32.673887" 410 | ] 411 | ], 412 | "judgment": "perfect", 413 | "problems": [] 414 | }, 415 | "reference_translation": "Ils n'ont pas expliqu\u00e9 pourquoi\u00a0?", 416 | "normalised_version": "" 417 | }, 418 | "12": { 419 | "language": "english", 420 | "original_text": "No explanations at all?", 421 | "preprocessed_text": "did they not explain why ? no explanations at all ?", 422 | "translated_text": "n' ont @-@ ils pas expliqu\u00e9 pourquoi ? pas d' explications ?", 423 | "postprocessed_text": "Pas d'explications ?", 424 | "composition_time": "2018-05-04T19:26:11.608082", 425 | "preprocessing_begin": "2018-05-04T19:26:11.648443", 426 | "preprocessing_end": "2018-05-04T19:26:13.795119", 427 | "translation_begin": "2018-05-04T19:26:13.795172", 428 | "translation_end": "2018-05-04T19:26:16.581810", 429 | "postprocessing_begin": "2018-05-04T19:26:16.582195", 430 | "postprocessing_end": "2018-05-04T19:26:16.616627", 431 | "sent_time": "2018-05-04T19:26:16.619023", 432 | "eval": { 433 | "problem_history": [], 434 | "verbatim_history": [], 435 | "verbatim": "", 436 | "judgment_history": [ 437 | [ 438 | "perfect", 439 | "2018-05-04T19:26:34.138424" 440 | ] 441 | ], 442 | "judgment": "perfect", 443 | "problems": [] 444 | }, 445 | "reference_translation": "Aucune explication\u00a0?", 446 | "normalised_version": "" 447 | }, 448 | "13": { 449 | "language": "french", 450 | "original_text": "Oui, bien s\u00fbr nous avons eu quelques explications .", 451 | "preprocessed_text": "pas d' explications ? oui , bien s\u00fbr nous avons eu quelques explications .", 452 | "translated_text": "no explanation ? yes , of course we had some explaining to do .", 453 | "postprocessed_text": "Yes, of course we had some explaining to do.", 454 | "composition_time": "2018-05-04T19:28:03.599613", 455 | "preprocessing_begin": "2018-05-04T19:28:03.648276", 456 | "preprocessing_end": "2018-05-04T19:28:06.243185", 457 | "translation_begin": "2018-05-04T19:28:06.243265", 458 | "translation_end": "2018-05-04T19:28:10.937404", 459 | "postprocessing_begin": "2018-05-04T19:28:10.937799", 460 | "postprocessing_end": "2018-05-04T19:28:10.973266", 461 | "sent_time": "2018-05-04T19:28:10.974833", 462 | "eval": { 463 | "problem_history": [ 464 | [ 465 | "coherence", 466 | "2018-05-04T19:28:24.101640", 467 | true 468 | ] 469 | ], 470 | "verbatim_history": [ 471 | [ 472 | "who was doing the explaining?", 473 | "2018-05-04T19:28:31.842302", 474 | "2018-05-04T19:28:31.842302" 475 | ] 476 | ], 477 | "verbatim": "who was doing the explaining?", 478 | "judgment_history": [ 479 | [ 480 | "medium", 481 | "2018-05-04T19:28:23.009517" 482 | ] 483 | ], 484 | "judgment": "medium", 485 | "problems": [ 486 | "coherence" 487 | ] 488 | }, 489 | "reference_translation": "Yes, of course we got some explanations.", 490 | "normalised_version": "Oui, bien s\u00fbr nous avons eu quelques explications." 491 | }, 492 | "14": { 493 | "language": "french", 494 | "original_text": "Nous n'avons pas, selon eux, r\u00e9pondu \u00e0 toutes leurs exigences techniques.", 495 | "preprocessed_text": "oui , bien s\u00fbr nous avons eu quelques explications . nous n' avons pas , selon eux , r\u00e9pondu \u00e0 toutes leurs exigences techniques .", 496 | "translated_text": "yes , of course we 've had some explaining . we don 't , according to them , responded to all their technical requirements .", 497 | "postprocessed_text": "We don't, according to them, responded to all their technical requirements.", 498 | "composition_time": "2018-05-04T19:28:03.599613", 499 | "preprocessing_begin": "2018-05-04T19:28:03.648276", 500 | "preprocessing_end": "2018-05-04T19:28:06.243185", 501 | "translation_begin": "2018-05-04T19:28:06.243265", 502 | "translation_end": "2018-05-04T19:28:10.937404", 503 | "postprocessing_begin": "2018-05-04T19:28:10.937799", 504 | "postprocessing_end": "2018-05-04T19:28:10.973266", 505 | "sent_time": "2018-05-04T19:28:10.975833", 506 | "eval": { 507 | "problem_history": [ 508 | [ 509 | "grammar", 510 | "2018-05-04T19:28:34.962245", 511 | true 512 | ], 513 | [ 514 | "word choice", 515 | "2018-05-04T19:29:34.213746", 516 | true 517 | ] 518 | ], 519 | "verbatim_history": [ 520 | [ 521 | "don't... responded. \"responded\" should be \"meet\"", 522 | "2018-05-04T19:29:44.638743", 523 | "2018-05-04T19:29:44.638743" 524 | ] 525 | ], 526 | "verbatim": "don't... responded. \"responded\" should be \"meet\"", 527 | "judgment_history": [ 528 | [ 529 | "medium", 530 | "2018-05-04T19:28:33.994763" 531 | ] 532 | ], 533 | "judgment": "medium", 534 | "problems": [ 535 | "grammar", 536 | "word choice" 537 | ] 538 | }, 539 | "reference_translation": "According to them, we didn\u2019t meet all their technical demands.", 540 | "normalised_version": "" 541 | }, 542 | "15": { 543 | "language": "french", 544 | "original_text": "de plus, nous \u00e9tions trop cher", 545 | "preprocessed_text": "nous n' avons pas , selon eux , r\u00e9pondu \u00e0 toutes leurs exigences techniques . de plus , nous \u00e9tions trop cher", 546 | "translated_text": "we don 't , according to them , responded to all their technical requirements . besides , we were too expensive .", 547 | "postprocessed_text": "Besides, we were too expensive.", 548 | "composition_time": "2018-05-04T19:28:03.599613", 549 | "preprocessing_begin": "2018-05-04T19:28:03.648276", 550 | "preprocessing_end": "2018-05-04T19:28:06.243185", 551 | "translation_begin": "2018-05-04T19:28:06.243265", 552 | "translation_end": "2018-05-04T19:28:10.937404", 553 | "postprocessing_begin": "2018-05-04T19:28:10.937799", 554 | "postprocessing_end": "2018-05-04T19:28:10.973266", 555 | "sent_time": "2018-05-04T19:28:10.976789", 556 | "eval": { 557 | "problem_history": [], 558 | "verbatim_history": [], 559 | "verbatim": "", 560 | "judgment_history": [ 561 | [ 562 | "perfect", 563 | "2018-05-04T19:29:20.562276" 564 | ] 565 | ], 566 | "judgment": "perfect", 567 | "problems": [] 568 | }, 569 | "reference_translation": "And we were too expensive.", 570 | "normalised_version": "De plus, nous \u00e9tions trop chers." 571 | }, 572 | "16": { 573 | "language": "english", 574 | "original_text": "Whose job was it to negotiate the contract?", 575 | "preprocessed_text": "besides , we were too expensive . whose job was it to negotiate the contract ?", 576 | "translated_text": "en plus , on \u00e9tait trop chers . c' \u00e9tait \u00e0 qui de n\u00e9gocier le contrat ?", 577 | "postprocessed_text": "C'\u00e9tait \u00e0 qui de n\u00e9gocier le contrat ?", 578 | "composition_time": "2018-05-04T19:29:14.970831", 579 | "preprocessing_begin": "2018-05-04T19:29:15.014455", 580 | "preprocessing_end": "2018-05-04T19:29:17.095713", 581 | "translation_begin": "2018-05-04T19:29:17.095793", 582 | "translation_end": "2018-05-04T19:29:20.505328", 583 | "postprocessing_begin": "2018-05-04T19:29:20.505780", 584 | "postprocessing_end": "2018-05-04T19:29:20.552772", 585 | "sent_time": "2018-05-04T19:29:20.554474", 586 | "eval": { 587 | "problem_history": [], 588 | "verbatim_history": [], 589 | "verbatim": "", 590 | "judgment_history": [], 591 | "judgment": null, 592 | "problems": [] 593 | }, 594 | "reference_translation": "C'\u00e9tait le travail de qui de n\u00e9gocier le contrat\u00a0?", 595 | "normalised_version": "" 596 | }, 597 | "17": { 598 | "language": "english", 599 | "original_text": "Surely there's some leeway to lower the prices a bit?", 600 | "preprocessed_text": "whose job was it to negotiate the contract ? surely there 's some leeway to lower the prices a bit ?", 601 | "translated_text": "quel travail \u00e9tait @-@ ce pour n\u00e9gocier le contrat ? il y a s\u00fbrement un peu de marge pour baisser un peu les prix ?", 602 | "postprocessed_text": "Il y a s\u00fbrement un peu de marge pour baisser un peu les prix ?", 603 | "composition_time": "2018-05-04T19:29:14.970831", 604 | "preprocessing_begin": "2018-05-04T19:29:15.014455", 605 | "preprocessing_end": "2018-05-04T19:29:17.095713", 606 | "translation_begin": "2018-05-04T19:29:17.095793", 607 | "translation_end": "2018-05-04T19:29:20.505328", 608 | "postprocessing_begin": "2018-05-04T19:29:20.505780", 609 | "postprocessing_end": "2018-05-04T19:29:20.552772", 610 | "sent_time": "2018-05-04T19:29:20.555580", 611 | "eval": { 612 | "problem_history": [], 613 | "verbatim_history": [], 614 | "verbatim": "", 615 | "judgment_history": [], 616 | "judgment": null, 617 | "problems": [] 618 | }, 619 | "reference_translation": "Il y avait s\u00fbrement une petite marge de man\u0153uvre pour baisser un peu les prix.", 620 | "normalised_version": "" 621 | } 622 | }, 623 | "final_evaluation_user1": {}, 624 | "final_evaluation_user2": { 625 | "interface": "", 626 | "meaning": "good", 627 | "coherence": "good", 628 | "grammaticality": "average", 629 | "tech": "There were no technical problems", 630 | "style": "excellent", 631 | "particular_problems": "a wrong word choice and grammatical mistake with \"responded\"", 632 | "timestamp": "2018-05-04T19:33:56.982300", 633 | "verbatim_quality": "", 634 | "would_use": true, 635 | "word_choice": "average", 636 | "technical_issue": "There were no technical problems" 637 | }, 638 | "fr_transl": true 639 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/dialogues/2018-05-17T13-10-59.820782_french_english_58_10.json: -------------------------------------------------------------------------------- 1 | { 2 | "start_time": "2018-05-17T13:10:59.820782", 3 | "end_time": null, 4 | "scenario": [ 5 | [ 6 | "You are both lost in a forest.", 7 | "Vous \u00eates tous les deux perdus dans une for\u00eat" 8 | ], 9 | [ 10 | "", 11 | "" 12 | ], 13 | [ 14 | "", 15 | "" 16 | ] 17 | ], 18 | "user1": { 19 | "role_num": 2, 20 | "lang": "french", 21 | "role": [ 22 | "", 23 | "" 24 | ], 25 | "initiated_dialogue": true, 26 | "turn_number": 2, 27 | "useragent": "Mozilla/5.0 (Android 8.0.0; Mobile; rv:62.0) Gecko/62.0 Firefox/62.0", 28 | "eval-stage": true 29 | }, 30 | "user2": { 31 | "lang": "english", 32 | "role": [ 33 | "", 34 | "" 35 | ], 36 | "rolenum": 1, 37 | "initiated_dialogue": false, 38 | "turn_number": 1, 39 | "useragent": "Mozilla/5.0 (Windows NT 6.1; rv:52.0) Gecko/20100101 Firefox/52.0", 40 | "eval-stage": true 41 | }, 42 | "translation_model": "baseline", 43 | "utterances": { 44 | "0": { 45 | "language": "english", 46 | "original_text": "Hello.", 47 | "preprocessed_text": "hello .", 48 | "translated_text": "bonjour .", 49 | "postprocessed_text": "Bonjour.", 50 | "composition_time": "2018-05-17T13:12:11.296929", 51 | "preprocessing_begin": "2018-05-17T13:12:11.367761", 52 | "preprocessing_end": "2018-05-17T13:12:13.705139", 53 | "translation_begin": "2018-05-17T13:12:13.705328", 54 | "translation_end": "2018-05-17T13:12:16.769327", 55 | "postprocessing_begin": "2018-05-17T13:12:16.769572", 56 | "postprocessing_end": "2018-05-17T13:12:16.815254", 57 | "sent_time": "2018-05-17T13:12:16.816634", 58 | "eval": { 59 | "judgment_history": [ 60 | [ 61 | "perfect", 62 | "2018-05-17T13:12:42.442480" 63 | ] 64 | ], 65 | "judgment": "perfect", 66 | "problems": [], 67 | "verbatim": "", 68 | "problem_history": [], 69 | "verbatim_history": [] 70 | }, 71 | "reference_translation": "Bonjour.", 72 | "normalised_version": "" 73 | }, 74 | "1": { 75 | "language": "english", 76 | "original_text": "I'm glad I've found you.", 77 | "preprocessed_text": "I 'm glad I 've found you .", 78 | "translated_text": "je suis contente de t' avoir trouv\u00e9 .", 79 | "postprocessed_text": "Je suis contente de t'avoir trouv\u00e9.", 80 | "composition_time": "2018-05-17T13:12:11.296929", 81 | "preprocessing_begin": "2018-05-17T13:12:11.367761", 82 | "preprocessing_end": "2018-05-17T13:12:13.705139", 83 | "translation_begin": "2018-05-17T13:12:13.705328", 84 | "translation_end": "2018-05-17T13:12:16.769327", 85 | "postprocessing_begin": "2018-05-17T13:12:16.769572", 86 | "postprocessing_end": "2018-05-17T13:12:16.815254", 87 | "sent_time": "2018-05-17T13:12:16.817255", 88 | "eval": { 89 | "judgment_history": [ 90 | [ 91 | "perfect", 92 | "2018-05-17T13:12:43.158475" 93 | ], 94 | [ 95 | "medium", 96 | "2018-05-17T13:12:44.211771" 97 | ] 98 | ], 99 | "judgment": "medium", 100 | "problems": [ 101 | "grammar" 102 | ], 103 | "verbatim": "", 104 | "problem_history": [ 105 | [ 106 | "grammar", 107 | "2018-05-17T13:12:47.361201", 108 | true 109 | ] 110 | ], 111 | "verbatim_history": [] 112 | }, 113 | "reference_translation": "Je suis heureux de vous avoir trouv\u00e9e.", 114 | "normalised_version": "" 115 | }, 116 | "2": { 117 | "language": "english", 118 | "original_text": "I've lost my way and have been walking in circles for ages.", 119 | "preprocessed_text": "I 've lost my way and have been walking in circles for ages .", 120 | "translated_text": "j' ai perdu mon chemin et j' ai tourn\u00e9 en rond depuis des lustres .", 121 | "postprocessed_text": "J'ai perdu mon chemin et j'ai tourn\u00e9 en rond depuis des lustres.", 122 | "composition_time": "2018-05-17T13:12:11.296929", 123 | "preprocessing_begin": "2018-05-17T13:12:11.367761", 124 | "preprocessing_end": "2018-05-17T13:12:13.705139", 125 | "translation_begin": "2018-05-17T13:12:13.705328", 126 | "translation_end": "2018-05-17T13:12:16.769327", 127 | "postprocessing_begin": "2018-05-17T13:12:16.769572", 128 | "postprocessing_end": "2018-05-17T13:12:16.815254", 129 | "sent_time": "2018-05-17T13:12:16.817880", 130 | "eval": { 131 | "judgment_history": [ 132 | [ 133 | "perfect", 134 | "2018-05-17T13:12:51.160035" 135 | ], 136 | [ 137 | "medium", 138 | "2018-05-17T13:12:53.310305" 139 | ] 140 | ], 141 | "judgment": "medium", 142 | "problems": [], 143 | "verbatim": "", 144 | "problem_history": [], 145 | "verbatim_history": [] 146 | }, 147 | "reference_translation": "Je me suis perdu et je tourne en rond depuis des heures.", 148 | "normalised_version": "" 149 | }, 150 | "3": { 151 | "language": "english", 152 | "original_text": "Do you know the way out of these trees?", 153 | "preprocessed_text": "do you know the way out of these trees ?", 154 | "translated_text": "tu sais comment sortir de ces arbres ?", 155 | "postprocessed_text": "Tu sais comment sortir de ces arbres ?", 156 | "composition_time": "2018-05-17T13:12:11.296929", 157 | "preprocessing_begin": "2018-05-17T13:12:11.367761", 158 | "preprocessing_end": "2018-05-17T13:12:13.705139", 159 | "translation_begin": "2018-05-17T13:12:13.705328", 160 | "translation_end": "2018-05-17T13:12:16.769327", 161 | "postprocessing_begin": "2018-05-17T13:12:16.769572", 162 | "postprocessing_end": "2018-05-17T13:12:16.815254", 163 | "sent_time": "2018-05-17T13:12:16.818455", 164 | "eval": { 165 | "judgment_history": [ 166 | [ 167 | "medium", 168 | "2018-05-17T13:12:56.763488" 169 | ] 170 | ], 171 | "judgment": "medium", 172 | "problems": [], 173 | "verbatim": "", 174 | "problem_history": [], 175 | "verbatim_history": [] 176 | }, 177 | "reference_translation": "Est-ce que vous savez comment sortir de cette for\u00eat ?", 178 | "normalised_version": "" 179 | }, 180 | "4": { 181 | "language": "french", 182 | "original_text": "Non, je ne suis jamais venu par ici, mais peut-\u00eatre qu'on peut essayer en avan\u00e7ant toujours dans la m\u00eame direction.", 183 | "preprocessed_text": "non , je ne suis jamais venu par ici , mais peut @-@ \u00eatre qu' on peut essayer en avan\u00e7ant toujours dans la m\u00eame direction .", 184 | "translated_text": "no , I 've never been here before , but maybe we can try moving forward in the same direction .", 185 | "postprocessed_text": "No, I've never been here before, but maybe we can try moving forward in the same direction.", 186 | "composition_time": "2018-05-17T13:13:37.047740", 187 | "preprocessing_begin": "2018-05-17T13:13:37.115225", 188 | "preprocessing_end": "2018-05-17T13:13:39.300345", 189 | "translation_begin": "2018-05-17T13:13:39.300449", 190 | "translation_end": "2018-05-17T13:13:40.971358", 191 | "postprocessing_begin": "2018-05-17T13:13:40.971567", 192 | "postprocessing_end": "2018-05-17T13:13:41.020685", 193 | "sent_time": "2018-05-17T13:13:41.021979", 194 | "eval": { 195 | "judgment_history": [ 196 | [ 197 | "perfect", 198 | "2018-05-17T13:14:32.145004" 199 | ] 200 | ], 201 | "judgment": "perfect", 202 | "problems": [], 203 | "verbatim": "", 204 | "problem_history": [], 205 | "verbatim_history": [] 206 | }, 207 | "reference_translation": "No, I\u2019ve never been by here before, but perhaps we can try to get out by continuing in the same direction.", 208 | "normalised_version": "" 209 | }, 210 | "5": { 211 | "language": "english", 212 | "original_text": "Yes, but which direction?", 213 | "preprocessed_text": "yes , but which direction ?", 214 | "translated_text": "oui , mais quelle direction ?", 215 | "postprocessed_text": "Oui, mais quelle direction ?", 216 | "composition_time": "2018-05-17T13:14:27.192146", 217 | "preprocessing_begin": "2018-05-17T13:14:27.258278", 218 | "preprocessing_end": "2018-05-17T13:14:29.813325", 219 | "translation_begin": "2018-05-17T13:14:29.813404", 220 | "translation_end": "2018-05-17T13:14:32.104262", 221 | "postprocessing_begin": "2018-05-17T13:14:32.104473", 222 | "postprocessing_end": "2018-05-17T13:14:32.138536", 223 | "sent_time": "2018-05-17T13:14:32.139573", 224 | "eval": { 225 | "judgment_history": [ 226 | [ 227 | "perfect", 228 | "2018-05-17T13:14:38.694679" 229 | ] 230 | ], 231 | "judgment": "perfect", 232 | "problems": [], 233 | "verbatim": "", 234 | "problem_history": [], 235 | "verbatim_history": [] 236 | }, 237 | "reference_translation": "Oui, mais quelle direction ?", 238 | "normalised_version": "" 239 | }, 240 | "6": { 241 | "language": "english", 242 | "original_text": "I think I came from that way, but over there also seems familiar.", 243 | "preprocessed_text": "I think I came from that way , but over there also seems familiar .", 244 | "translated_text": "je crois que je viens de cette fa\u00e7on , mais l\u00e0 @-@ bas me semble aussi familier .", 245 | "postprocessed_text": "Je crois que je viens de cette fa\u00e7on, mais l\u00e0-bas me semble aussi familier.", 246 | "composition_time": "2018-05-17T13:14:27.192146", 247 | "preprocessing_begin": "2018-05-17T13:14:27.258278", 248 | "preprocessing_end": "2018-05-17T13:14:29.813325", 249 | "translation_begin": "2018-05-17T13:14:29.813404", 250 | "translation_end": "2018-05-17T13:14:32.104262", 251 | "postprocessing_begin": "2018-05-17T13:14:32.104473", 252 | "postprocessing_end": "2018-05-17T13:14:32.138536", 253 | "sent_time": "2018-05-17T13:14:32.140064", 254 | "eval": { 255 | "judgment_history": [ 256 | [ 257 | "medium", 258 | "2018-05-17T13:14:40.560119" 259 | ], 260 | [ 261 | "poor", 262 | "2018-05-17T13:14:41.761007" 263 | ], 264 | [ 265 | "perfect", 266 | "2018-05-17T13:14:45.551208" 267 | ], 268 | [ 269 | "medium", 270 | "2018-05-17T13:14:46.158901" 271 | ] 272 | ], 273 | "judgment": "medium", 274 | "problems": [ 275 | "word choice" 276 | ], 277 | "verbatim": "", 278 | "problem_history": [ 279 | [ 280 | "word choice", 281 | "2018-05-17T13:14:47.066438", 282 | true 283 | ] 284 | ], 285 | "verbatim_history": [] 286 | }, 287 | "reference_translation": "Je pense que je viens de par-l\u00e0 mais par l\u00e0-bas \u00e7a me dit quelque chose aussi.", 288 | "normalised_version": "" 289 | }, 290 | "7": { 291 | "language": "french", 292 | "original_text": "La mousse n'est pas cens\u00e9e toujours pousser au nord ?", 293 | "preprocessed_text": "la mousse n' est pas cens\u00e9e toujours pousser au nord ?", 294 | "translated_text": "isn 't the moss still supposed to grow north ?", 295 | "postprocessed_text": "Isn't the moss still supposed to grow north?", 296 | "composition_time": "2018-05-17T13:15:37.987658", 297 | "preprocessing_begin": "2018-05-17T13:15:38.037263", 298 | "preprocessing_end": "2018-05-17T13:15:40.560801", 299 | "translation_begin": "2018-05-17T13:15:40.560943", 300 | "translation_end": "2018-05-17T13:15:43.215831", 301 | "postprocessing_begin": "2018-05-17T13:15:43.216048", 302 | "postprocessing_end": "2018-05-17T13:15:43.249577", 303 | "sent_time": "2018-05-17T13:15:43.250607", 304 | "eval": { 305 | "judgment_history": [ 306 | [ 307 | "poor", 308 | "2018-05-17T13:16:26.990058" 309 | ] 310 | ], 311 | "judgment": "poor", 312 | "problems": [ 313 | "meaning" 314 | ], 315 | "verbatim": "", 316 | "problem_history": [ 317 | [ 318 | "meaning", 319 | "2018-05-17T13:16:29.955752", 320 | true 321 | ] 322 | ], 323 | "verbatim_history": [] 324 | }, 325 | "reference_translation": "Isn\u2019t moss always meant to grow Northwards?", 326 | "normalised_version": "" 327 | }, 328 | "8": { 329 | "language": "french", 330 | "original_text": "Au pire on choisit au hasard, on finira bien par tomber sur des habitations.", 331 | "preprocessed_text": "au pire on choisit au hasard , on finira bien par tomber sur des habit@@ ations .", 332 | "translated_text": "at the worst , we pick at random , we 'll end up on people 's lives .", 333 | "postprocessed_text": "At the worst, we pick at random, we'll end up on people's lives.", 334 | "composition_time": "2018-05-17T13:15:37.987658", 335 | "preprocessing_begin": "2018-05-17T13:15:38.037263", 336 | "preprocessing_end": "2018-05-17T13:15:40.560801", 337 | "translation_begin": "2018-05-17T13:15:40.560943", 338 | "translation_end": "2018-05-17T13:15:43.215831", 339 | "postprocessing_begin": "2018-05-17T13:15:43.216048", 340 | "postprocessing_end": "2018-05-17T13:15:43.249577", 341 | "sent_time": "2018-05-17T13:15:43.251073", 342 | "eval": { 343 | "judgment_history": [ 344 | [ 345 | "poor", 346 | "2018-05-17T13:16:35.443537" 347 | ] 348 | ], 349 | "judgment": "poor", 350 | "problems": [ 351 | "meaning" 352 | ], 353 | "verbatim": "", 354 | "problem_history": [ 355 | [ 356 | "meaning", 357 | "2018-05-17T13:16:38.420636", 358 | true 359 | ] 360 | ], 361 | "verbatim_history": [] 362 | }, 363 | "reference_translation": "At the very least, we can randomly choose and we\u2019ll eventually come across some houses.", 364 | "normalised_version": "" 365 | }, 366 | "9": { 367 | "language": "english", 368 | "original_text": "OK.", 369 | "preprocessed_text": "OK .", 370 | "translated_text": "ok .", 371 | "postprocessed_text": "Ok.", 372 | "composition_time": "2018-05-17T13:18:22.245084", 373 | "preprocessing_begin": "2018-05-17T13:18:22.308962", 374 | "preprocessing_end": "2018-05-17T13:18:24.388587", 375 | "translation_begin": "2018-05-17T13:18:24.388697", 376 | "translation_end": "2018-05-17T13:18:28.538530", 377 | "postprocessing_begin": "2018-05-17T13:18:28.538769", 378 | "postprocessing_end": "2018-05-17T13:18:28.594215", 379 | "sent_time": "2018-05-17T13:18:28.595568", 380 | "eval": { 381 | "judgment_history": [ 382 | [ 383 | "perfect", 384 | "2018-05-17T13:18:38.739959" 385 | ] 386 | ], 387 | "judgment": "perfect", 388 | "problems": [], 389 | "verbatim": "", 390 | "problem_history": [], 391 | "verbatim_history": [] 392 | }, 393 | "reference_translation": "OK.", 394 | "normalised_version": "" 395 | }, 396 | "10": { 397 | "language": "english", 398 | "original_text": "I suggest that we go that way and stick closely together.", 399 | "preprocessed_text": "I suggest that we go that way and stick closely together .", 400 | "translated_text": "je sugg\u00e8re qu' on aille par l\u00e0 , et qu' on reste ensemble .", 401 | "postprocessed_text": "Je sugg\u00e8re qu'on aille par l\u00e0, et qu'on reste ensemble.", 402 | "composition_time": "2018-05-17T13:18:22.245084", 403 | "preprocessing_begin": "2018-05-17T13:18:22.308962", 404 | "preprocessing_end": "2018-05-17T13:18:24.388587", 405 | "translation_begin": "2018-05-17T13:18:24.388697", 406 | "translation_end": "2018-05-17T13:18:28.538530", 407 | "postprocessing_begin": "2018-05-17T13:18:28.538769", 408 | "postprocessing_end": "2018-05-17T13:18:28.594215", 409 | "sent_time": "2018-05-17T13:18:28.596213", 410 | "eval": { 411 | "judgment_history": [ 412 | [ 413 | "perfect", 414 | "2018-05-17T13:18:39.973099" 415 | ] 416 | ], 417 | "judgment": "perfect", 418 | "problems": [], 419 | "verbatim": "", 420 | "problem_history": [], 421 | "verbatim_history": [] 422 | }, 423 | "reference_translation": "Je propose que nous allions par-l\u00e0 et que nous restions ensemble.", 424 | "normalised_version": "" 425 | }, 426 | "11": { 427 | "language": "english", 428 | "original_text": "The light is beginning to fade and we don't want to loose touch with each other.", 429 | "preprocessed_text": "the light is beginning to fade and we don 't want to loose touch with each other .", 430 | "translated_text": "la lumi\u00e8re commence \u00e0 s' estom@@ per et nous ne voulons pas perdre contact l' un avec l' autre .", 431 | "postprocessed_text": "La lumi\u00e8re commence \u00e0 s'estomper et nous ne voulons pas perdre contact l'un avec l'autre.", 432 | "composition_time": "2018-05-17T13:18:22.245084", 433 | "preprocessing_begin": "2018-05-17T13:18:22.308962", 434 | "preprocessing_end": "2018-05-17T13:18:24.388587", 435 | "translation_begin": "2018-05-17T13:18:24.388697", 436 | "translation_end": "2018-05-17T13:18:28.538530", 437 | "postprocessing_begin": "2018-05-17T13:18:28.538769", 438 | "postprocessing_end": "2018-05-17T13:18:28.594215", 439 | "sent_time": "2018-05-17T13:18:28.596808", 440 | "eval": { 441 | "judgment_history": [ 442 | [ 443 | "medium", 444 | "2018-05-17T13:18:42.372271" 445 | ] 446 | ], 447 | "judgment": "medium", 448 | "problems": [], 449 | "verbatim": "", 450 | "problem_history": [], 451 | "verbatim_history": [] 452 | }, 453 | "reference_translation": "La lumi\u00e8re commence \u00e0 baisser et il ne faudrait pas que nous nous perdions de vue.", 454 | "normalised_version": "The light is beginning to fade and we don't want to lose touch with each other." 455 | }, 456 | "12": { 457 | "language": "english", 458 | "original_text": "Do you hae any food or drink with you?", 459 | "preprocessed_text": "do you hae any food or drink with you ?", 460 | "translated_text": "vous buvez quelque chose ou vous buvez avec vous ?", 461 | "postprocessed_text": "Vous buvez quelque chose ou vous buvez avec vous ?", 462 | "composition_time": "2018-05-17T13:18:22.245084", 463 | "preprocessing_begin": "2018-05-17T13:18:22.308962", 464 | "preprocessing_end": "2018-05-17T13:18:24.388587", 465 | "translation_begin": "2018-05-17T13:18:24.388697", 466 | "translation_end": "2018-05-17T13:18:28.538530", 467 | "postprocessing_begin": "2018-05-17T13:18:28.538769", 468 | "postprocessing_end": "2018-05-17T13:18:28.594215", 469 | "sent_time": "2018-05-17T13:18:28.597433", 470 | "eval": { 471 | "judgment_history": [ 472 | [ 473 | "medium", 474 | "2018-05-17T13:18:53.051193" 475 | ] 476 | ], 477 | "judgment": "medium", 478 | "problems": [], 479 | "verbatim": "", 480 | "problem_history": [], 481 | "verbatim_history": [] 482 | }, 483 | "reference_translation": "Avez-vous quelque chose \u00e0 manger ou \u00e0 boire ?", 484 | "normalised_version": "Do you have any food or drink with you?" 485 | }, 486 | "13": { 487 | "language": "french", 488 | "original_text": "Oui, j'ai toujours de l'eau dans mon sac.", 489 | "preprocessed_text": "oui , j' ai toujours de l' eau dans mon sac .", 490 | "translated_text": "yes , I still have water in my bag .", 491 | "postprocessed_text": "Yes, I still have water in my bag.", 492 | "composition_time": "2018-05-17T13:19:37.908541", 493 | "preprocessing_begin": "2018-05-17T13:19:37.969646", 494 | "preprocessing_end": "2018-05-17T13:19:40.798738", 495 | "translation_begin": "2018-05-17T13:19:40.798840", 496 | "translation_end": "2018-05-17T13:19:42.242635", 497 | "postprocessing_begin": "2018-05-17T13:19:42.242910", 498 | "postprocessing_end": "2018-05-17T13:19:42.295643", 499 | "sent_time": "2018-05-17T13:19:42.297058", 500 | "eval": { 501 | "judgment_history": [ 502 | [ 503 | "perfect", 504 | "2018-05-17T13:19:57.345061" 505 | ] 506 | ], 507 | "judgment": "perfect", 508 | "problems": [], 509 | "verbatim": "", 510 | "problem_history": [], 511 | "verbatim_history": [] 512 | }, 513 | "reference_translation": "Yes, I always have water in my bag.", 514 | "normalised_version": "" 515 | }, 516 | "14": { 517 | "language": "french", 518 | "original_text": "Vous avez soif ?", 519 | "preprocessed_text": "vous avez soif ?", 520 | "translated_text": "thirsty ?", 521 | "postprocessed_text": "Thirsty?", 522 | "composition_time": "2018-05-17T13:19:37.908541", 523 | "preprocessing_begin": "2018-05-17T13:19:37.969646", 524 | "preprocessing_end": "2018-05-17T13:19:40.798738", 525 | "translation_begin": "2018-05-17T13:19:40.798840", 526 | "translation_end": "2018-05-17T13:19:42.242635", 527 | "postprocessing_begin": "2018-05-17T13:19:42.242910", 528 | "postprocessing_end": "2018-05-17T13:19:42.295643", 529 | "sent_time": "2018-05-17T13:19:42.297795", 530 | "eval": { 531 | "judgment_history": [ 532 | [ 533 | "perfect", 534 | "2018-05-17T13:19:58.424734" 535 | ] 536 | ], 537 | "judgment": "perfect", 538 | "problems": [], 539 | "verbatim": "", 540 | "problem_history": [], 541 | "verbatim_history": [] 542 | }, 543 | "reference_translation": "Are you thirsty?", 544 | "normalised_version": "" 545 | }, 546 | "15": { 547 | "language": "english", 548 | "original_text": "I am thirsty but I was hoping for something a bit stronger that water.", 549 | "preprocessed_text": "I am thirsty but I was hoping for something a bit stronger that water .", 550 | "translated_text": "j' ai soif , mais j' esp\u00e9rais quelque chose d' un peu plus fort cette eau .", 551 | "postprocessed_text": "J'ai soif, mais j'esp\u00e9rais quelque chose d'un peu plus fort cette eau.", 552 | "composition_time": "2018-05-17T13:20:33.115384", 553 | "preprocessing_begin": "2018-05-17T13:20:33.173157", 554 | "preprocessing_end": "2018-05-17T13:20:35.271479", 555 | "translation_begin": "2018-05-17T13:20:35.271570", 556 | "translation_end": "2018-05-17T13:20:37.428804", 557 | "postprocessing_begin": "2018-05-17T13:20:37.429020", 558 | "postprocessing_end": "2018-05-17T13:20:37.471498", 559 | "sent_time": "2018-05-17T13:20:37.472466", 560 | "eval": { 561 | "judgment_history": [ 562 | [ 563 | "medium", 564 | "2018-05-17T13:21:54.068112" 565 | ] 566 | ], 567 | "judgment": "medium", 568 | "problems": [], 569 | "verbatim": "", 570 | "problem_history": [], 571 | "verbatim_history": [] 572 | }, 573 | "reference_translation": "J\u2019ai soif mais j'esp\u00e9rais quelque chose d'un peu plus fort que de l\u2019eau.", 574 | "normalised_version": "" 575 | }, 576 | "16": { 577 | "language": "english", 578 | "original_text": "Anyway, can you let me have a bit of your water?", 579 | "preprocessed_text": "anyway , can you let me have a bit of your water ?", 580 | "translated_text": "puis @-@ je avoir un peu de votre eau ?", 581 | "postprocessed_text": "Puis-je avoir un peu de votre eau ?", 582 | "composition_time": "2018-05-17T13:20:33.115384", 583 | "preprocessing_begin": "2018-05-17T13:20:33.173157", 584 | "preprocessing_end": "2018-05-17T13:20:35.271479", 585 | "translation_begin": "2018-05-17T13:20:35.271570", 586 | "translation_end": "2018-05-17T13:20:37.428804", 587 | "postprocessing_begin": "2018-05-17T13:20:37.429020", 588 | "postprocessing_end": "2018-05-17T13:20:37.471498", 589 | "sent_time": "2018-05-17T13:20:37.472910", 590 | "eval": { 591 | "judgment_history": [ 592 | [ 593 | "perfect", 594 | "2018-05-17T13:21:54.971338" 595 | ] 596 | ], 597 | "judgment": "perfect", 598 | "problems": [], 599 | "verbatim": "", 600 | "problem_history": [], 601 | "verbatim_history": [] 602 | }, 603 | "reference_translation": "Tant pis, est-ce que vous pouvez me donner un peu de votre eau ?", 604 | "normalised_version": "" 605 | }, 606 | "17": { 607 | "language": "french", 608 | "original_text": "Oui, tenez.", 609 | "preprocessed_text": "oui , tenez .", 610 | "translated_text": "yeah , here .", 611 | "postprocessed_text": "Yeah, here.", 612 | "composition_time": "2018-05-17T13:21:47.931341", 613 | "preprocessing_begin": "2018-05-17T13:21:48.016992", 614 | "preprocessing_end": "2018-05-17T13:21:50.220128", 615 | "translation_begin": "2018-05-17T13:21:50.220209", 616 | "translation_end": "2018-05-17T13:21:52.368240", 617 | "postprocessing_begin": "2018-05-17T13:21:52.368628", 618 | "postprocessing_end": "2018-05-17T13:21:52.404449", 619 | "sent_time": "2018-05-17T13:21:52.405668", 620 | "eval": { 621 | "judgment_history": [ 622 | [ 623 | "perfect", 624 | "2018-05-17T13:22:24.178561" 625 | ] 626 | ], 627 | "judgment": "perfect", 628 | "problems": [], 629 | "verbatim": "", 630 | "problem_history": [], 631 | "verbatim_history": [] 632 | }, 633 | "reference_translation": "Yes, here you go.", 634 | "normalised_version": "" 635 | }, 636 | "18": { 637 | "language": "french", 638 | "original_text": "Et si on reste coinc\u00e9 ici trop longtemps on pourra toujours essayer de faire de l'alcool de m\u00fbres.", 639 | "preprocessed_text": "et si on reste coinc\u00e9 ici trop longtemps on pourra toujours essayer de faire de l' alcool de m\u00fbres .", 640 | "translated_text": "and if we stay stuck here too long , we can still try black@@ berries .", 641 | "postprocessed_text": "And if we stay stuck here too long, we can still try blackberries.", 642 | "composition_time": "2018-05-17T13:21:47.931341", 643 | "preprocessing_begin": "2018-05-17T13:21:48.016992", 644 | "preprocessing_end": "2018-05-17T13:21:50.220128", 645 | "translation_begin": "2018-05-17T13:21:50.220209", 646 | "translation_end": "2018-05-17T13:21:52.368240", 647 | "postprocessing_begin": "2018-05-17T13:21:52.368628", 648 | "postprocessing_end": "2018-05-17T13:21:52.404449", 649 | "sent_time": "2018-05-17T13:21:52.406183", 650 | "eval": { 651 | "judgment_history": [ 652 | [ 653 | "perfect", 654 | "2018-05-17T13:22:27.843254" 655 | ] 656 | ], 657 | "judgment": "perfect", 658 | "problems": [], 659 | "verbatim": "", 660 | "problem_history": [], 661 | "verbatim_history": [] 662 | }, 663 | "reference_translation": "And if we\u2019re stuck here too long, we can always try to make alcohol out of blackberries.", 664 | "normalised_version": "" 665 | } 666 | }, 667 | "final_evaluation_user1": { 668 | "style": "average", 669 | "would_use": true, 670 | "grammaticality": "good", 671 | "verbatim_quality": "", 672 | "meaning": "average", 673 | "particular_problems": "", 674 | "interface": "mon royaume pour un bouton envoyer !", 675 | "tech": "There were no technical problems", 676 | "coherence": "good", 677 | "timestamp": "2018-05-17T13:24:02.380058", 678 | "word_choice": "average", 679 | "technical_issue": "There were no technical problems" 680 | }, 681 | "final_evaluation_user2": { 682 | "style": "good", 683 | "would_use": true, 684 | "grammaticality": "good", 685 | "verbatim_quality": "overall ok, but with a couple of sentences when the meaning was unclear", 686 | "meaning": "poor", 687 | "particular_problems": "there were two sentences that just didn't make any sense to me", 688 | "interface": "", 689 | "tech": "There were no technical problems", 690 | "coherence": "good", 691 | "timestamp": "2018-05-17T13:24:24.820617", 692 | "word_choice": "good", 693 | "technical_issue": "There were no technical problems" 694 | }, 695 | "fr_transl": true 696 | } -------------------------------------------------------------------------------- /DiaBLa-corpus/dialogues/2018-05-14T13-21-20.795702_french_english_50_3.json: -------------------------------------------------------------------------------- 1 | { 2 | "start_time": "2018-05-14T13:21:20.795702", 3 | "end_time": null, 4 | "scenario": [ 5 | [ 6 | "You are on holiday by the pool.", 7 | "Vous \u00eates en vacances \u00e0 c\u00f4t\u00e9 de la piscine." 8 | ], 9 | [ 10 | "You are trying to relax and the other person wants to do something else.", 11 | "Vous essayez de vous reposer et l'autre personne veut faire autre chose." 12 | ], 13 | [ 14 | "You want to do something else and the other person is trying to relax", 15 | "Vous voulez faire autre chose et l'autre personne essaie de se reposer." 16 | ] 17 | ], 18 | "user1": { 19 | "useragent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:59.0) Gecko/20100101 Firefox/59.0", 20 | "eval-stage": true, 21 | "role_num": 2, 22 | "role": [ 23 | "You want to do something else and the other person is trying to relax", 24 | "Vous voulez faire autre chose et l'autre personne essaie de se reposer." 25 | ], 26 | "lang": "french", 27 | "initiated_dialogue": [ 28 | false, 29 | true 30 | ], 31 | "turn_number": 1 32 | }, 33 | "user2": { 34 | "useragent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/11.1 Safari/605.1.15", 35 | "rolenum": 1, 36 | "eval-stage": true, 37 | "lang": "english", 38 | "role": [ 39 | "You are trying to relax and the other person wants to do something else.", 40 | "Vous essayez de vous reposer et l'autre personne veut faire autre chose." 41 | ], 42 | "initiated_dialogue": [ 43 | false, 44 | true 45 | ], 46 | "turn_number": 2 47 | }, 48 | "translation_model": "2to2", 49 | "utterances": { 50 | "0": { 51 | "language": "french", 52 | "original_text": "Salut Caroline, tu ne t'ennuies pas un peu ici ?", 53 | "preprocessed_text": " salut Caroline , tu ne t' ennuies pas un peu ici ?", 54 | "translated_text": "jum@@ ble hey , Caroline , don 't you get bored a bit here ?", 55 | "postprocessed_text": "Hey, Caroline, don't you get bored a bit here?", 56 | "composition_time": "2018-05-14T13:22:36.771882", 57 | "preprocessing_begin": "2018-05-14T13:22:36.853223", 58 | "preprocessing_end": "2018-05-14T13:22:39.620081", 59 | "translation_begin": "2018-05-14T13:22:39.620282", 60 | "translation_end": "2018-05-14T13:22:41.293608", 61 | "postprocessing_begin": "2018-05-14T13:22:41.294073", 62 | "postprocessing_end": "2018-05-14T13:22:41.345538", 63 | "sent_time": "2018-05-14T13:22:41.347260", 64 | "eval": { 65 | "problems": [ 66 | "grammar" 67 | ], 68 | "judgment_history": [ 69 | [ 70 | "medium", 71 | "2018-05-14T13:23:26.499676" 72 | ] 73 | ], 74 | "verbatim": "\"don't you get\" -> I would expect 'aren't you getting'", 75 | "verbatim_history": [ 76 | [ 77 | "\"don't you get\" -> I would expect 'aren't you getting'", 78 | "2018-05-14T13:23:56.597866", 79 | "2018-05-14T13:23:56.597866" 80 | ] 81 | ], 82 | "judgment": "medium", 83 | "problem_history": [ 84 | [ 85 | "grammar", 86 | "2018-05-14T13:23:26.501638", 87 | true 88 | ] 89 | ] 90 | }, 91 | "reference_translation": "Hi Caroline, aren\u2019t you a bit bored here?", 92 | "normalised_version": "" 93 | }, 94 | "1": { 95 | "language": "english", 96 | "original_text": "I'm ok actually.", 97 | "preprocessed_text": "hey , Caroline , don 't you get bored a bit here ? I 'm ok actually .", 98 | "translated_text": "h\u00e9 , Caroline , tu ne t' ennuies pas un peu ici ? je vais bien , en fait .", 99 | "postprocessed_text": "Je vais bien, en fait.", 100 | "composition_time": "2018-05-14T13:23:18.962221", 101 | "preprocessing_begin": "2018-05-14T13:23:19.027159", 102 | "preprocessing_end": "2018-05-14T13:23:21.186368", 103 | "translation_begin": "2018-05-14T13:23:21.186518", 104 | "translation_end": "2018-05-14T13:23:26.435061", 105 | "postprocessing_begin": "2018-05-14T13:23:26.435609", 106 | "postprocessing_end": "2018-05-14T13:23:26.487710", 107 | "sent_time": "2018-05-14T13:23:26.489671", 108 | "eval": { 109 | "problems": [ 110 | "word choice" 111 | ], 112 | "judgment_history": [ 113 | [ 114 | "medium", 115 | "2018-05-14T13:29:04.805988" 116 | ] 117 | ], 118 | "verbatim": "Je ne vois pas trop \u00e0 quoi \"en fait\" se rapporte", 119 | "verbatim_history": [ 120 | [ 121 | "Je ne vois pas trop \u00e0 quoi \"en fait\" se rapporte", 122 | "2018-05-14T13:29:35.339259", 123 | "2018-05-14T13:29:35.339259" 124 | ] 125 | ], 126 | "judgment": "medium", 127 | "problem_history": [ 128 | [ 129 | "word choice", 130 | "2018-05-14T13:29:14.686156", 131 | true 132 | ] 133 | ] 134 | }, 135 | "reference_translation": "En fait \u00e7a va.", 136 | "normalised_version": "" 137 | }, 138 | "2": { 139 | "language": "english", 140 | "original_text": "I'm just enjoying the beautiful weather and the calm breeze.", 141 | "preprocessed_text": "I 'm ok actually . I 'm just enjoying the beautiful weather and the calm breeze .", 142 | "translated_text": "je vais bien , en fait . j' appr\u00e9cie juste le beau temps et la brise calme .", 143 | "postprocessed_text": "J'appr\u00e9cie juste le beau temps et la brise calme.", 144 | "composition_time": "2018-05-14T13:23:18.962221", 145 | "preprocessing_begin": "2018-05-14T13:23:19.027159", 146 | "preprocessing_end": "2018-05-14T13:23:21.186368", 147 | "translation_begin": "2018-05-14T13:23:21.186518", 148 | "translation_end": "2018-05-14T13:23:26.435061", 149 | "postprocessing_begin": "2018-05-14T13:23:26.435609", 150 | "postprocessing_end": "2018-05-14T13:23:26.487710", 151 | "sent_time": "2018-05-14T13:23:26.490951", 152 | "eval": { 153 | "problems": [], 154 | "judgment_history": [ 155 | [ 156 | "perfect", 157 | "2018-05-14T13:24:39.401322" 158 | ] 159 | ], 160 | "verbatim": "", 161 | "verbatim_history": [], 162 | "judgment": "perfect", 163 | "problem_history": [] 164 | }, 165 | "reference_translation": "Je profite simplement du beau temps et de cette petite brise.", 166 | "normalised_version": "" 167 | }, 168 | "3": { 169 | "language": "english", 170 | "original_text": "What else could you ask for?", 171 | "preprocessed_text": "I 'm just enjoying the beautiful weather and the calm breeze . what else could you ask for ?", 172 | "translated_text": "j' appr\u00e9cie juste le beau temps et la brise calme . que demander d' autre ?", 173 | "postprocessed_text": "Que demander d'autre ?", 174 | "composition_time": "2018-05-14T13:23:18.962221", 175 | "preprocessing_begin": "2018-05-14T13:23:19.027159", 176 | "preprocessing_end": "2018-05-14T13:23:21.186368", 177 | "translation_begin": "2018-05-14T13:23:21.186518", 178 | "translation_end": "2018-05-14T13:23:26.435061", 179 | "postprocessing_begin": "2018-05-14T13:23:26.435609", 180 | "postprocessing_end": "2018-05-14T13:23:26.487710", 181 | "sent_time": "2018-05-14T13:23:26.492212", 182 | "eval": { 183 | "problems": [], 184 | "judgment_history": [ 185 | [ 186 | "perfect", 187 | "2018-05-14T13:24:40.550956" 188 | ] 189 | ], 190 | "verbatim": "", 191 | "verbatim_history": [], 192 | "judgment": "perfect", 193 | "problem_history": [] 194 | }, 195 | "reference_translation": "Que pourrais-je demander de plus\u00a0?", 196 | "normalised_version": "" 197 | }, 198 | "4": { 199 | "language": "french", 200 | "original_text": "J'aimerais bien aller me promener un peu, pour changer.", 201 | "preprocessed_text": "que demander d' autre ? j' aimerais bien aller me promener un peu , pour changer .", 202 | "translated_text": "what else can I ask for ? I 'd like to go for a walk for a change .", 203 | "postprocessed_text": "I'd like to go for a walk for a change.", 204 | "composition_time": "2018-05-14T13:24:03.189413", 205 | "preprocessing_begin": "2018-05-14T13:24:03.266862", 206 | "preprocessing_end": "2018-05-14T13:24:05.868109", 207 | "translation_begin": "2018-05-14T13:24:05.868220", 208 | "translation_end": "2018-05-14T13:24:07.788450", 209 | "postprocessing_begin": "2018-05-14T13:24:07.788854", 210 | "postprocessing_end": "2018-05-14T13:24:07.850493", 211 | "sent_time": "2018-05-14T13:24:07.852042", 212 | "eval": { 213 | "problems": [], 214 | "judgment_history": [ 215 | [ 216 | "perfect", 217 | "2018-05-14T13:26:44.128439" 218 | ] 219 | ], 220 | "verbatim": "", 221 | "verbatim_history": [], 222 | "judgment": "perfect", 223 | "problem_history": [] 224 | }, 225 | "reference_translation": "I\u2019d like to go have bit of a walk, to get a change of scenery.", 226 | "normalised_version": "" 227 | }, 228 | "5": { 229 | "language": "english", 230 | "original_text": "But aren't you tired?", 231 | "preprocessed_text": "I 'd like to go for a walk for a change . but aren 't you tired ?", 232 | "translated_text": "j' aimerais aller me promener pour changer . mais tu n' es pas fatigu\u00e9 ?", 233 | "postprocessed_text": "Mais tu n'es pas fatigu\u00e9 ?", 234 | "composition_time": "2018-05-14T13:24:47.060862", 235 | "preprocessing_begin": "2018-05-14T13:24:47.120707", 236 | "preprocessing_end": "2018-05-14T13:24:49.552716", 237 | "translation_begin": "2018-05-14T13:24:49.552801", 238 | "translation_end": "2018-05-14T13:24:52.120562", 239 | "postprocessing_begin": "2018-05-14T13:24:52.120975", 240 | "postprocessing_end": "2018-05-14T13:24:52.162481", 241 | "sent_time": "2018-05-14T13:24:52.163672", 242 | "eval": { 243 | "problems": [], 244 | "judgment_history": [ 245 | [ 246 | "perfect", 247 | "2018-05-14T13:26:08.378532" 248 | ] 249 | ], 250 | "verbatim": "", 251 | "verbatim_history": [], 252 | "judgment": "perfect", 253 | "problem_history": [] 254 | }, 255 | "reference_translation": "Mais n\u2019es-tu pas fatigu\u00e9\u00a0?", 256 | "normalised_version": "" 257 | }, 258 | "6": { 259 | "language": "english", 260 | "original_text": "We had a huge lunch...", 261 | "preprocessed_text": "but aren 't you tired ? we had a huge lunch ...", 262 | "translated_text": "mais tu n' es pas fatigu\u00e9 ? on a eu un \u00e9norme d\u00e9jeuner ...", 263 | "postprocessed_text": "On a eu un \u00e9norme d\u00e9jeuner...", 264 | "composition_time": "2018-05-14T13:24:47.060862", 265 | "preprocessing_begin": "2018-05-14T13:24:47.120707", 266 | "preprocessing_end": "2018-05-14T13:24:49.552716", 267 | "translation_begin": "2018-05-14T13:24:49.552801", 268 | "translation_end": "2018-05-14T13:24:52.120562", 269 | "postprocessing_begin": "2018-05-14T13:24:52.120975", 270 | "postprocessing_end": "2018-05-14T13:24:52.162481", 271 | "sent_time": "2018-05-14T13:24:52.164330", 272 | "eval": { 273 | "problems": [], 274 | "judgment_history": [ 275 | [ 276 | "perfect", 277 | "2018-05-14T13:26:11.426129" 278 | ] 279 | ], 280 | "verbatim": "", 281 | "verbatim_history": [], 282 | "judgment": "perfect", 283 | "problem_history": [] 284 | }, 285 | "reference_translation": "Nous avons fait un repas copieux\u2026", 286 | "normalised_version": "" 287 | }, 288 | "7": { 289 | "language": "french", 290 | "original_text": "Justement, la promenade c'est bon pour la digestion !", 291 | "preprocessed_text": "on a eu un \u00e9norme d\u00e9jeuner ... justement , la promenade c' est bon pour la digestion !", 292 | "translated_text": "we had a huge lunch ... exactly , the boardwalk 's good for the digestion !", 293 | "postprocessed_text": "Exactly, the boardwalk's good for the digestion!", 294 | "composition_time": "2018-05-14T13:25:39.147050", 295 | "preprocessing_begin": "2018-05-14T13:25:39.220544", 296 | "preprocessing_end": "2018-05-14T13:25:41.604416", 297 | "translation_begin": "2018-05-14T13:25:41.604529", 298 | "translation_end": "2018-05-14T13:25:43.380230", 299 | "postprocessing_begin": "2018-05-14T13:25:43.380671", 300 | "postprocessing_end": "2018-05-14T13:25:43.431306", 301 | "sent_time": "2018-05-14T13:25:43.433520", 302 | "eval": { 303 | "problems": [ 304 | "grammar" 305 | ], 306 | "judgment_history": [ 307 | [ 308 | "medium", 309 | "2018-05-14T13:26:30.640944" 310 | ] 311 | ], 312 | "verbatim": "\"the\" shouldn't be there", 313 | "verbatim_history": [ 314 | [ 315 | "\"the\" shouldn't be there", 316 | "2018-05-14T13:26:41.179051", 317 | "2018-05-14T13:26:41.179051" 318 | ] 319 | ], 320 | "judgment": "medium", 321 | "problem_history": [ 322 | [ 323 | "grammar", 324 | "2018-05-14T13:26:31.747404", 325 | true 326 | ] 327 | ] 328 | }, 329 | "reference_translation": "Exactly! Walking is good for digestion.", 330 | "normalised_version": "" 331 | }, 332 | "8": { 333 | "language": "english", 334 | "original_text": "I find that sleeping can be quite efficient too!", 335 | "preprocessed_text": "exactly , the boardwalk 's good for the digestion ! I find that sleeping can be quite efficient too !", 336 | "translated_text": "exactement , la promenade de nuit est bonne pour la digestion ! je trouve que dormir peut \u00eatre assez efficace aussi !", 337 | "postprocessed_text": "Je trouve que dormir peut \u00eatre assez efficace aussi !", 338 | "composition_time": "2018-05-14T13:26:11.534023", 339 | "preprocessing_begin": "2018-05-14T13:26:11.596958", 340 | "preprocessing_end": "2018-05-14T13:26:13.782893", 341 | "translation_begin": "2018-05-14T13:26:13.782997", 342 | "translation_end": "2018-05-14T13:26:18.057087", 343 | "postprocessing_begin": "2018-05-14T13:26:18.057801", 344 | "postprocessing_end": "2018-05-14T13:26:18.103034", 345 | "sent_time": "2018-05-14T13:26:18.104735", 346 | "eval": { 347 | "problems": [], 348 | "judgment_history": [ 349 | [ 350 | "perfect", 351 | "2018-05-14T13:28:58.983000" 352 | ] 353 | ], 354 | "verbatim": "", 355 | "verbatim_history": [], 356 | "judgment": "perfect", 357 | "problem_history": [] 358 | }, 359 | "reference_translation": "Je trouve que dormir peut \u00eatre tr\u00e8s efficace aussi\u00a0!", 360 | "normalised_version": "" 361 | }, 362 | "9": { 363 | "language": "english", 364 | "original_text": "Why are you so keen to go for a walk?", 365 | "preprocessed_text": "I find that sleeping can be quite efficient too ! why are you so keen to go for a walk ?", 366 | "translated_text": "je trouve que dormir peut \u00eatre assez efficace aussi ! pourquoi es @-@ tu si press\u00e9 d' aller te promener ?", 367 | "postprocessed_text": "Pourquoi es-tu si press\u00e9 d'aller te promener ?", 368 | "composition_time": "2018-05-14T13:26:11.534023", 369 | "preprocessing_begin": "2018-05-14T13:26:11.596958", 370 | "preprocessing_end": "2018-05-14T13:26:13.782893", 371 | "translation_begin": "2018-05-14T13:26:13.782997", 372 | "translation_end": "2018-05-14T13:26:18.057087", 373 | "postprocessing_begin": "2018-05-14T13:26:18.057801", 374 | "postprocessing_end": "2018-05-14T13:26:18.103034", 375 | "sent_time": "2018-05-14T13:26:18.105868", 376 | "eval": { 377 | "problems": [], 378 | "judgment_history": [ 379 | [ 380 | "perfect", 381 | "2018-05-14T13:29:00.600651" 382 | ] 383 | ], 384 | "verbatim": "", 385 | "verbatim_history": [], 386 | "judgment": "perfect", 387 | "problem_history": [] 388 | }, 389 | "reference_translation": "Pourquoi as-tu tellement envie d\u2019aller te promener\u00a0?", 390 | "normalised_version": "" 391 | }, 392 | "10": { 393 | "language": "french", 394 | "original_text": "Faire des longueurs dans une petite piscine, ce n'est pas tr\u00e8s original.", 395 | "preprocessed_text": "pourquoi es @-@ tu si press\u00e9 d' aller te promener ? faire des longueurs dans une petite piscine , ce n' est pas tr\u00e8s original .", 396 | "translated_text": "why are you so anxious to go for a walk ? doing laps in a small pool , that 's not very original .", 397 | "postprocessed_text": "Doing laps in a small pool, that's not very original.", 398 | "composition_time": "2018-05-14T13:27:33.924324", 399 | "preprocessing_begin": "2018-05-14T13:27:34.010932", 400 | "preprocessing_end": "2018-05-14T13:27:36.900840", 401 | "translation_begin": "2018-05-14T13:27:36.901022", 402 | "translation_end": "2018-05-14T13:27:39.342296", 403 | "postprocessing_begin": "2018-05-14T13:27:39.342707", 404 | "postprocessing_end": "2018-05-14T13:27:39.382158", 405 | "sent_time": "2018-05-14T13:27:39.383701", 406 | "eval": { 407 | "problems": [], 408 | "judgment_history": [ 409 | [ 410 | "perfect", 411 | "2018-05-14T13:29:58.070307" 412 | ] 413 | ], 414 | "verbatim": "", 415 | "verbatim_history": [], 416 | "judgment": "perfect", 417 | "problem_history": [] 418 | }, 419 | "reference_translation": "Doing lengths in a small pool isn\u2019t very original.", 420 | "normalised_version": "" 421 | }, 422 | "11": { 423 | "language": "french", 424 | "original_text": "Alors qu'il y a un petit chemin pour la for\u00eat juste \u00e0 c\u00f4t\u00e9.", 425 | "preprocessed_text": "faire des longueurs dans une petite piscine , ce n' est pas tr\u00e8s original . alors qu' il y a un petit chemin pour la for\u00eat juste \u00e0 c\u00f4t\u00e9 .", 426 | "translated_text": "doing laps in a small pool , that 's not very original . while there 's a little forest road right next to it .", 427 | "postprocessed_text": "While there's a little forest road right next to it.", 428 | "composition_time": "2018-05-14T13:28:14.223409", 429 | "preprocessing_begin": "2018-05-14T13:28:14.289867", 430 | "preprocessing_end": "2018-05-14T13:28:16.786870", 431 | "translation_begin": "2018-05-14T13:28:16.787187", 432 | "translation_end": "2018-05-14T13:28:18.843127", 433 | "postprocessing_begin": "2018-05-14T13:28:18.843627", 434 | "postprocessing_end": "2018-05-14T13:28:18.890634", 435 | "sent_time": "2018-05-14T13:28:18.892557", 436 | "eval": { 437 | "problems": [ 438 | "coherence" 439 | ], 440 | "judgment_history": [ 441 | [ 442 | "medium", 443 | "2018-05-14T13:29:58.073100" 444 | ] 445 | ], 446 | "verbatim": "\"while\"", 447 | "verbatim_history": [ 448 | [ 449 | "\"while\"", 450 | "2018-05-14T13:29:58.077480", 451 | "2018-05-14T13:29:58.077480" 452 | ] 453 | ], 454 | "judgment": "medium", 455 | "problem_history": [ 456 | [ 457 | "coherence", 458 | "2018-05-14T13:29:58.075317", 459 | true 460 | ] 461 | ] 462 | }, 463 | "reference_translation": "Whilst there\u2019s a little path leading to the forest right there.", 464 | "normalised_version": "" 465 | }, 466 | "12": { 467 | "language": "english", 468 | "original_text": "I wouldn't mind if you brought me back something cool to drink.", 469 | "preprocessed_text": "while there 's a little forest road right next to it . I wouldn 't mind if you brought me back something cool to drink .", 470 | "translated_text": "pendant qu' il y a une petite route de for\u00eat juste \u00e0 c\u00f4t\u00e9 . \u00e7a ne me d\u00e9range pas si tu me ram\u00e8nes un truc cool \u00e0 boire .", 471 | "postprocessed_text": "\u00c7a ne me d\u00e9range pas si tu me ram\u00e8nes un truc cool \u00e0 boire.", 472 | "composition_time": "2018-05-14T13:29:49.644677", 473 | "preprocessing_begin": "2018-05-14T13:29:49.718606", 474 | "preprocessing_end": "2018-05-14T13:29:52.310295", 475 | "translation_begin": "2018-05-14T13:29:52.310391", 476 | "translation_end": "2018-05-14T13:29:58.026294", 477 | "postprocessing_begin": "2018-05-14T13:29:58.026701", 478 | "postprocessing_end": "2018-05-14T13:29:58.062165", 479 | "sent_time": "2018-05-14T13:29:58.063126", 480 | "eval": { 481 | "problems": [], 482 | "judgment_history": [ 483 | [ 484 | "perfect", 485 | "2018-05-14T13:33:12.808873" 486 | ] 487 | ], 488 | "verbatim": "", 489 | "verbatim_history": [], 490 | "judgment": "perfect", 491 | "problem_history": [] 492 | }, 493 | "reference_translation": "Je n\u2019aurais rien contre le fait que tu me rapportes quelque chose de frais \u00e0 boire.", 494 | "normalised_version": "" 495 | }, 496 | "13": { 497 | "language": "english", 498 | "original_text": "But I quite like being here thanks.", 499 | "preprocessed_text": "I wouldn 't mind if you brought me back something cool to drink . but I quite like being here thanks .", 500 | "translated_text": "\u00e7a ne me d\u00e9range pas que tu me ram\u00e8nes un truc cool \u00e0 boire . mais j' aime \u00eatre ici , merci .", 501 | "postprocessed_text": "Mais j'aime \u00eatre ici, merci.", 502 | "composition_time": "2018-05-14T13:29:49.644677", 503 | "preprocessing_begin": "2018-05-14T13:29:49.718606", 504 | "preprocessing_end": "2018-05-14T13:29:52.310295", 505 | "translation_begin": "2018-05-14T13:29:52.310391", 506 | "translation_end": "2018-05-14T13:29:58.026294", 507 | "postprocessing_begin": "2018-05-14T13:29:58.026701", 508 | "postprocessing_end": "2018-05-14T13:29:58.062165", 509 | "sent_time": "2018-05-14T13:29:58.063532", 510 | "eval": { 511 | "problems": [], 512 | "judgment_history": [ 513 | [ 514 | "perfect", 515 | "2018-05-14T13:33:14.007125" 516 | ] 517 | ], 518 | "verbatim": "", 519 | "verbatim_history": [], 520 | "judgment": "perfect", 521 | "problem_history": [] 522 | }, 523 | "reference_translation": "Mais j\u2019aime bien \u00eatre ici, merci.", 524 | "normalised_version": "" 525 | }, 526 | "14": { 527 | "language": "english", 528 | "original_text": "It's too shady in the forest for my liking.", 529 | "preprocessed_text": "but I quite like being here thanks . it 's too shady in the forest for my liking .", 530 | "translated_text": "mais j' aime \u00eatre ici , merci . c' est trop louche dans la for\u00eat \u00e0 mon go\u00fbt .", 531 | "postprocessed_text": "C'est trop louche dans la for\u00eat \u00e0 mon go\u00fbt.", 532 | "composition_time": "2018-05-14T13:29:49.644677", 533 | "preprocessing_begin": "2018-05-14T13:29:49.718606", 534 | "preprocessing_end": "2018-05-14T13:29:52.310295", 535 | "translation_begin": "2018-05-14T13:29:52.310391", 536 | "translation_end": "2018-05-14T13:29:58.026294", 537 | "postprocessing_begin": "2018-05-14T13:29:58.026701", 538 | "postprocessing_end": "2018-05-14T13:29:58.062165", 539 | "sent_time": "2018-05-14T13:29:58.063904", 540 | "eval": { 541 | "problems": [ 542 | "word choice" 543 | ], 544 | "judgment_history": [ 545 | [ 546 | "medium", 547 | "2018-05-14T13:32:37.246479" 548 | ] 549 | ], 550 | "verbatim": "", 551 | "verbatim_history": [], 552 | "judgment": "medium", 553 | "problem_history": [ 554 | [ 555 | "word choice", 556 | "2018-05-14T13:33:06.347562", 557 | true 558 | ] 559 | ] 560 | }, 561 | "reference_translation": "Il y a trop d\u2019ombre dans la for\u00eat \u00e0 mon go\u00fbt.", 562 | "normalised_version": "" 563 | }, 564 | "15": { 565 | "language": "french", 566 | "original_text": "Alors tant pis, je vais te laisser et on se retrouve en fin d'apr\u00e8s-midi.", 567 | "preprocessed_text": "c' est trop louche dans la for\u00eat \u00e0 mon go\u00fbt . alors tant pis , je vais te laisser et on se retrouve en fin d' apr\u00e8s @-@ midi .", 568 | "translated_text": "it 's too fishy in the forest for my taste . then I 'll leave you and I 'll meet you at the end of the afternoon .", 569 | "postprocessed_text": "Then I'll leave you and I'll meet you at the end of the afternoon.", 570 | "composition_time": "2018-05-14T13:31:59.463985", 571 | "preprocessing_begin": "2018-05-14T13:31:59.536573", 572 | "preprocessing_end": "2018-05-14T13:32:02.130850", 573 | "translation_begin": "2018-05-14T13:32:02.130987", 574 | "translation_end": "2018-05-14T13:32:06.485618", 575 | "postprocessing_begin": "2018-05-14T13:32:06.486021", 576 | "postprocessing_end": "2018-05-14T13:32:06.522741", 577 | "sent_time": "2018-05-14T13:32:06.524254", 578 | "eval": { 579 | "problems": [], 580 | "judgment_history": [ 581 | [ 582 | "perfect", 583 | "2018-05-14T13:32:38.299139" 584 | ] 585 | ], 586 | "verbatim": "", 587 | "verbatim_history": [], 588 | "judgment": "perfect", 589 | "problem_history": [] 590 | }, 591 | "reference_translation": "Then never mind! I\u2019m going to leave you to it and we can meet up late afternoon.", 592 | "normalised_version": "" 593 | }, 594 | "16": { 595 | "language": "french", 596 | "original_text": "Salut !", 597 | "preprocessed_text": "alors tant pis , je vais te laisser et on se retrouve en fin d' apr\u00e8s @-@ midi . salut !", 598 | "translated_text": "anyway , I 'm going to leave you and I 'll meet you at the end of the afternoon . hi !", 599 | "postprocessed_text": "Hi!", 600 | "composition_time": "2018-05-14T13:31:59.463985", 601 | "preprocessing_begin": "2018-05-14T13:31:59.536573", 602 | "preprocessing_end": "2018-05-14T13:32:02.130850", 603 | "translation_begin": "2018-05-14T13:32:02.130987", 604 | "translation_end": "2018-05-14T13:32:06.485618", 605 | "postprocessing_begin": "2018-05-14T13:32:06.486021", 606 | "postprocessing_end": "2018-05-14T13:32:06.522741", 607 | "sent_time": "2018-05-14T13:32:06.525279", 608 | "eval": { 609 | "problems": [ 610 | "coherence", 611 | "meaning" 612 | ], 613 | "judgment_history": [ 614 | [ 615 | "poor", 616 | "2018-05-14T13:32:41.488830" 617 | ] 618 | ], 619 | "verbatim": "should be \"bye\"", 620 | "verbatim_history": [ 621 | [ 622 | "should be \"bye\"", 623 | "2018-05-14T13:32:51.775937", 624 | "2018-05-14T13:32:51.775937" 625 | ] 626 | ], 627 | "judgment": "poor", 628 | "problem_history": [ 629 | [ 630 | "coherence", 631 | "2018-05-14T13:32:42.624129", 632 | true 633 | ], 634 | [ 635 | "meaning", 636 | "2018-05-14T13:32:45.281453", 637 | true 638 | ] 639 | ] 640 | }, 641 | "reference_translation": "See you!", 642 | "normalised_version": "" 643 | }, 644 | "17": { 645 | "language": "english", 646 | "original_text": "Wait!", 647 | "preprocessed_text": "hi ! wait !", 648 | "translated_text": "salut ! attends !", 649 | "postprocessed_text": "Attends !", 650 | "composition_time": "2018-05-14T13:32:32.630744", 651 | "preprocessing_begin": "2018-05-14T13:32:32.703319", 652 | "preprocessing_end": "2018-05-14T13:32:35.051133", 653 | "translation_begin": "2018-05-14T13:32:35.051257", 654 | "translation_end": "2018-05-14T13:32:38.252501", 655 | "postprocessing_begin": "2018-05-14T13:32:38.252909", 656 | "postprocessing_end": "2018-05-14T13:32:38.289230", 657 | "sent_time": "2018-05-14T13:32:38.290801", 658 | "eval": { 659 | "problems": [], 660 | "judgment_history": [ 661 | [ 662 | "perfect", 663 | "2018-05-14T13:33:24.143112" 664 | ] 665 | ], 666 | "verbatim": "", 667 | "verbatim_history": [], 668 | "judgment": "perfect", 669 | "problem_history": [] 670 | }, 671 | "reference_translation": "Attends\u00a0!", 672 | "normalised_version": "" 673 | }, 674 | "18": { 675 | "language": "english", 676 | "original_text": "Will you get me something from the shop round the corner?", 677 | "preprocessed_text": "wait ! will you get me something from the shop round the corner ?", 678 | "translated_text": "attendez ! apportez @-@ moi quelque chose du magasin au coin de la rue .", 679 | "postprocessed_text": "Apportez-moi quelque chose du magasin au coin de la rue.", 680 | "composition_time": "2018-05-14T13:32:32.630744", 681 | "preprocessing_begin": "2018-05-14T13:32:32.703319", 682 | "preprocessing_end": "2018-05-14T13:32:35.051133", 683 | "translation_begin": "2018-05-14T13:32:35.051257", 684 | "translation_end": "2018-05-14T13:32:38.252501", 685 | "postprocessing_begin": "2018-05-14T13:32:38.252909", 686 | "postprocessing_end": "2018-05-14T13:32:38.289230", 687 | "sent_time": "2018-05-14T13:32:38.291805", 688 | "eval": { 689 | "problems": [ 690 | "coherence" 691 | ], 692 | "judgment_history": [ 693 | [ 694 | "medium", 695 | "2018-05-14T13:33:25.519623" 696 | ] 697 | ], 698 | "verbatim": "Passage du 'tu' au 'vous'", 699 | "verbatim_history": [ 700 | [ 701 | "Passage du 'tu' au 'vous'", 702 | "2018-05-14T13:33:49.002196", 703 | "2018-05-14T13:33:49.002196" 704 | ] 705 | ], 706 | "judgment": "medium", 707 | "problem_history": [ 708 | [ 709 | "coherence", 710 | "2018-05-14T13:33:29.464990", 711 | true 712 | ] 713 | ] 714 | }, 715 | "reference_translation": "Pourrais-tu me rapporter quelque chose du magasin au coin\u00a0?", 716 | "normalised_version": "" 717 | }, 718 | "19": { 719 | "language": "english", 720 | "original_text": "Pretty please!", 721 | "preprocessed_text": "will you get me something from the shop round the corner ? pretty please !", 722 | "translated_text": "apportez @-@ moi quelque chose du magasin au coin de la rue . s' il vous pla\u00eet !", 723 | "postprocessed_text": "S'il vous pla\u00eet !", 724 | "composition_time": "2018-05-14T13:32:32.630744", 725 | "preprocessing_begin": "2018-05-14T13:32:32.703319", 726 | "preprocessing_end": "2018-05-14T13:32:35.051133", 727 | "translation_begin": "2018-05-14T13:32:35.051257", 728 | "translation_end": "2018-05-14T13:32:38.252501", 729 | "postprocessing_begin": "2018-05-14T13:32:38.252909", 730 | "postprocessing_end": "2018-05-14T13:32:38.289230", 731 | "sent_time": "2018-05-14T13:32:38.292783", 732 | "eval": { 733 | "problems": [], 734 | "judgment_history": [ 735 | [ 736 | "medium", 737 | "2018-05-14T13:33:50.937583" 738 | ], 739 | [ 740 | "perfect", 741 | "2018-05-14T13:33:59.226821" 742 | ] 743 | ], 744 | "verbatim": "", 745 | "verbatim_history": [], 746 | "judgment": "perfect", 747 | "problem_history": [] 748 | }, 749 | "reference_translation": "S\u2019il te pla\u00eet\u00a0!", 750 | "normalised_version": "" 751 | } 752 | }, 753 | "final_evaluation_user1": { 754 | "verbatim_quality": "tb", 755 | "timestamp": "2018-05-14T13:35:43.884719", 756 | "meaning": "good", 757 | "tech": "There were no technical problems", 758 | "grammaticality": "excellent", 759 | "coherence": "good", 760 | "particular_problems": "tu vs. vous ; familier vs. soutenu", 761 | "interface": "tb", 762 | "would_use": true, 763 | "style": "average", 764 | "word_choice": "good", 765 | "technical_issue": "There were no technical problems" 766 | }, 767 | "final_evaluation_user2": { 768 | "verbatim_quality": "very good globally.", 769 | "timestamp": "2018-05-14T13:35:09.259732", 770 | "meaning": "excellent", 771 | "tech": "There were no technical problems", 772 | "grammaticality": "good", 773 | "coherence": "good", 774 | "particular_problems": "some choices were not very coherent, such as \"hi\" instead of \"bye\", and a link made between sentences using \"while\".", 775 | "interface": "", 776 | "would_use": true, 777 | "style": "excellent", 778 | "word_choice": "excellent", 779 | "technical_issue": "There were no technical problems" 780 | }, 781 | "fr_transl": true 782 | } --------------------------------------------------------------------------------