├── LICENSE.md ├── README.md ├── _config.yml ├── candidate_generation ├── .idea │ ├── .name │ ├── EntityExtraction.iml │ ├── encodings.xml │ ├── misc.xml │ ├── modules.xml │ ├── scopes │ │ └── scope_settings.xml │ ├── vcs.xml │ └── workspace.xml ├── DataPreprocessing │ ├── Clean.py │ ├── Partition.py │ ├── Partition.pyc │ ├── Reformat.py │ ├── StopWords.py │ ├── StopWords.pyc │ └── __init__.py ├── EntityExtraction │ ├── EntityRelation.py │ ├── HeapDictionary2.py │ ├── HeapDictionary2.pyc │ ├── PPV │ │ ├── PPV.py │ │ ├── PPV.pyc │ │ ├── __init__.py │ │ ├── __init__.pyc │ │ └── ppv.txt │ ├── Patterns │ │ ├── ConsecutiveCapital.py │ │ ├── ConsecutiveCapital.pyc │ │ ├── ConsecutiveNouns.py │ │ ├── ConsecutiveNouns.pyc │ │ ├── VerbPhrase.py │ │ ├── VerbPhrase.pyc │ │ ├── __init__.py │ │ └── __init__.pyc │ ├── PostProcess │ │ ├── PostProcess.py │ │ ├── PostProcess.pyc │ │ ├── PostProcess2.py │ │ ├── __init__.py │ │ └── __init__.pyc │ ├── RelationExtraction │ │ ├── RelationConstruction.py │ │ ├── RelationConstruction.pyc │ │ ├── __init__.py │ │ └── __init__.pyc │ ├── ScoringFunctions.py │ ├── ScoringFunctions.pyc │ ├── Segmentor.py │ ├── Segmentor.pyc │ ├── Word.py │ ├── Word.pyc │ └── __init__.py ├── FrequentPhraseMining │ ├── BitVector.py │ ├── BitVector.pyc │ ├── FrequentPatternMining.py │ ├── TrieCounter.py │ └── __init__.py ├── PPV │ ├── PPV.py │ ├── __init__.py │ └── ppv.txt ├── Patterns │ ├── ConsecutiveCapital.py │ ├── ConsecutiveNouns.py │ ├── VerbPhrase.py │ └── __init__.py ├── README.txt ├── RelationExtraction │ ├── RelationConstruction.py │ └── __init__.py └── stopwords │ ├── de.txt │ ├── en.txt │ ├── fi.txt │ ├── fr.txt │ ├── jp.txt │ ├── stop-words-collection-2014-02-24.zip │ └── stop-words-collection-2014-02-24 │ ├── project-information.txt │ └── stop-words │ ├── stop-words_arabic_1_ar.txt │ ├── stop-words_arabic_2_ar.txt │ ├── stop-words_brazil_1_br.txt │ ├── stop-words_bulgarian_1_bg.txt │ ├── stop-words_catalan_1_ca.txt │ ├── stop-words_chinese_1_zh.txt │ ├── stop-words_czech_1_cz.txt │ ├── stop-words_czech_2_cz.txt │ ├── stop-words_czech_3_cz.txt │ ├── stop-words_danish_1_da.txt │ ├── stop-words_dutch_1_nl.txt │ ├── stop-words_dutch_2_nl.txt │ ├── stop-words_english_1_en.txt │ ├── stop-words_english_2_en.txt │ ├── stop-words_english_3_en.txt │ ├── stop-words_english_4_google_en.txt │ ├── stop-words_english_5_en.txt │ ├── stop-words_english_6_en.txt │ ├── stop-words_finnish_1_fi.txt │ ├── stop-words_finnish_2_fi.txt │ ├── stop-words_french_1_fr.txt │ ├── stop-words_french_2_fr.txt │ ├── stop-words_german_1_de.txt │ ├── stop-words_german_2_de.txt │ ├── stop-words_greek_1_el.txt │ ├── stop-words_greek_2_el.txt │ ├── stop-words_hindi_1_hi.txt │ ├── stop-words_hungarian_1_hu.txt │ ├── stop-words_hungarian_2_hu.txt │ ├── stop-words_indonesian_1_id.txt │ ├── stop-words_italian_1_it.txt │ ├── stop-words_italian_2_it.txt │ ├── stop-words_japanese_1_ja.txt │ ├── stop-words_latvian_1_lv.txt │ ├── stop-words_norwegian_1_no.txt │ ├── stop-words_norwegian_2_no.txt │ ├── stop-words_persian_1_fa.txt │ ├── stop-words_polish_1_pl.txt │ ├── stop-words_polish_2_pl.txt │ ├── stop-words_polish_3_pl.txt │ ├── stop-words_portugese_1_pt.txt │ ├── stop-words_portugese_2_pt.txt │ ├── stop-words_romanian_1_ro.txt │ ├── stop-words_russian_1_ru.txt │ ├── stop-words_russian_2_ru.txt │ ├── stop-words_slovak_1_sk.txt │ ├── stop-words_slovak_2_sk.txt │ ├── stop-words_spanish_1_es.txt │ ├── stop-words_spanish_2_es.txt │ ├── stop-words_swedish_1_sv.txt │ ├── stop-words_swedish_2_sv.txt │ ├── stop-words_turkish_1_tr.txt │ └── stop-words_turkish_2_tr.txt ├── data ├── nyt │ └── type_tid.txt ├── stopwords.txt ├── tweet │ └── type_tid.txt └── yelp │ └── type_tid.txt ├── entity_linking └── EntityLinking.py ├── run.sh └── src ├── algorithm.py ├── algorithm.pyc ├── clustype.py ├── clustype.pyc ├── data_model.py ├── data_model.pyc ├── evaluation.py ├── evaluation.pyc ├── step0-graph_construction.py └── step1-entity_recognition.py /LICENSE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/LICENSE.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/README.md -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/_config.yml -------------------------------------------------------------------------------- /candidate_generation/.idea/.name: -------------------------------------------------------------------------------- 1 | EntityExtraction -------------------------------------------------------------------------------- /candidate_generation/.idea/EntityExtraction.iml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/EntityExtraction.iml -------------------------------------------------------------------------------- /candidate_generation/.idea/encodings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/encodings.xml -------------------------------------------------------------------------------- /candidate_generation/.idea/misc.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/misc.xml -------------------------------------------------------------------------------- /candidate_generation/.idea/modules.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/modules.xml -------------------------------------------------------------------------------- /candidate_generation/.idea/scopes/scope_settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/scopes/scope_settings.xml -------------------------------------------------------------------------------- /candidate_generation/.idea/vcs.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/vcs.xml -------------------------------------------------------------------------------- /candidate_generation/.idea/workspace.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/.idea/workspace.xml -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/Clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/DataPreprocessing/Clean.py -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/Partition.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/DataPreprocessing/Partition.py -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/Partition.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/DataPreprocessing/Partition.pyc -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/Reformat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/DataPreprocessing/Reformat.py -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/StopWords.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/DataPreprocessing/StopWords.py -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/StopWords.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/DataPreprocessing/StopWords.pyc -------------------------------------------------------------------------------- /candidate_generation/DataPreprocessing/__init__.py: -------------------------------------------------------------------------------- 1 | __author__ = 'ahmed' 2 | -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/EntityRelation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/EntityRelation.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/HeapDictionary2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/HeapDictionary2.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/HeapDictionary2.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/HeapDictionary2.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PPV/PPV.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PPV/PPV.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PPV/PPV.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PPV/PPV.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PPV/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PPV/__init__.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PPV/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PPV/__init__.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PPV/ppv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PPV/ppv.txt -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/ConsecutiveCapital.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/ConsecutiveCapital.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/ConsecutiveCapital.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/ConsecutiveCapital.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/ConsecutiveNouns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/ConsecutiveNouns.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/ConsecutiveNouns.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/ConsecutiveNouns.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/VerbPhrase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/VerbPhrase.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/VerbPhrase.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/VerbPhrase.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/__init__.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Patterns/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Patterns/__init__.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PostProcess/PostProcess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PostProcess/PostProcess.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PostProcess/PostProcess.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PostProcess/PostProcess.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PostProcess/PostProcess2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PostProcess/PostProcess2.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PostProcess/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PostProcess/__init__.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/PostProcess/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/PostProcess/__init__.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/RelationExtraction/RelationConstruction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/RelationExtraction/RelationConstruction.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/RelationExtraction/RelationConstruction.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/RelationExtraction/RelationConstruction.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/RelationExtraction/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/RelationExtraction/__init__.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/RelationExtraction/__init__.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/RelationExtraction/__init__.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/ScoringFunctions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/ScoringFunctions.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/ScoringFunctions.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/ScoringFunctions.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Segmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Segmentor.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Segmentor.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Segmentor.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Word.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Word.py -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/Word.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/EntityExtraction/Word.pyc -------------------------------------------------------------------------------- /candidate_generation/EntityExtraction/__init__.py: -------------------------------------------------------------------------------- 1 | __author__ = 'ahmed' 2 | -------------------------------------------------------------------------------- /candidate_generation/FrequentPhraseMining/BitVector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/FrequentPhraseMining/BitVector.py -------------------------------------------------------------------------------- /candidate_generation/FrequentPhraseMining/BitVector.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/FrequentPhraseMining/BitVector.pyc -------------------------------------------------------------------------------- /candidate_generation/FrequentPhraseMining/FrequentPatternMining.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/FrequentPhraseMining/FrequentPatternMining.py -------------------------------------------------------------------------------- /candidate_generation/FrequentPhraseMining/TrieCounter.py: -------------------------------------------------------------------------------- 1 | __author__ = 'ahmed' 2 | -------------------------------------------------------------------------------- /candidate_generation/FrequentPhraseMining/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/FrequentPhraseMining/__init__.py -------------------------------------------------------------------------------- /candidate_generation/PPV/PPV.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/PPV/PPV.py -------------------------------------------------------------------------------- /candidate_generation/PPV/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/PPV/__init__.py -------------------------------------------------------------------------------- /candidate_generation/PPV/ppv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/PPV/ppv.txt -------------------------------------------------------------------------------- /candidate_generation/Patterns/ConsecutiveCapital.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/Patterns/ConsecutiveCapital.py -------------------------------------------------------------------------------- /candidate_generation/Patterns/ConsecutiveNouns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/Patterns/ConsecutiveNouns.py -------------------------------------------------------------------------------- /candidate_generation/Patterns/VerbPhrase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/Patterns/VerbPhrase.py -------------------------------------------------------------------------------- /candidate_generation/Patterns/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/Patterns/__init__.py -------------------------------------------------------------------------------- /candidate_generation/README.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/README.txt -------------------------------------------------------------------------------- /candidate_generation/RelationExtraction/RelationConstruction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/RelationExtraction/RelationConstruction.py -------------------------------------------------------------------------------- /candidate_generation/RelationExtraction/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/RelationExtraction/__init__.py -------------------------------------------------------------------------------- /candidate_generation/stopwords/de.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/de.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/fi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/fi.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/fr.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/jp.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/jp.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24.zip -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/project-information.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/project-information.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_arabic_1_ar.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_arabic_1_ar.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_arabic_2_ar.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_arabic_2_ar.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_brazil_1_br.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_brazil_1_br.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_bulgarian_1_bg.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_bulgarian_1_bg.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_catalan_1_ca.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_catalan_1_ca.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_chinese_1_zh.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_chinese_1_zh.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_czech_1_cz.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_czech_1_cz.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_czech_2_cz.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_czech_2_cz.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_czech_3_cz.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_czech_3_cz.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_danish_1_da.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_danish_1_da.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_dutch_1_nl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_dutch_1_nl.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_dutch_2_nl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_dutch_2_nl.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_1_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_1_en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_2_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_2_en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_3_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_3_en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_4_google_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_4_google_en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_5_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_5_en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_6_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_english_6_en.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_finnish_1_fi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_finnish_1_fi.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_finnish_2_fi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_finnish_2_fi.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_french_1_fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_french_1_fr.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_french_2_fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_french_2_fr.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_german_1_de.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_german_1_de.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_german_2_de.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_german_2_de.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_greek_1_el.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_greek_1_el.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_greek_2_el.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_greek_2_el.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_hindi_1_hi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_hindi_1_hi.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_hungarian_1_hu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_hungarian_1_hu.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_hungarian_2_hu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_hungarian_2_hu.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_indonesian_1_id.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_indonesian_1_id.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_italian_1_it.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_italian_1_it.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_italian_2_it.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_italian_2_it.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_japanese_1_ja.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_japanese_1_ja.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_latvian_1_lv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_latvian_1_lv.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_norwegian_1_no.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_norwegian_1_no.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_norwegian_2_no.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_norwegian_2_no.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_persian_1_fa.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_persian_1_fa.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_polish_1_pl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_polish_1_pl.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_polish_2_pl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_polish_2_pl.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_polish_3_pl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_polish_3_pl.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_portugese_1_pt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_portugese_1_pt.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_portugese_2_pt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_portugese_2_pt.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_romanian_1_ro.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_romanian_1_ro.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_russian_1_ru.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_russian_1_ru.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_russian_2_ru.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_russian_2_ru.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_slovak_1_sk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_slovak_1_sk.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_slovak_2_sk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_slovak_2_sk.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_spanish_1_es.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_spanish_1_es.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_spanish_2_es.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_spanish_2_es.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_swedish_1_sv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_swedish_1_sv.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_swedish_2_sv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_swedish_2_sv.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_turkish_1_tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_turkish_1_tr.txt -------------------------------------------------------------------------------- /candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_turkish_2_tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/candidate_generation/stopwords/stop-words-collection-2014-02-24/stop-words/stop-words_turkish_2_tr.txt -------------------------------------------------------------------------------- /data/nyt/type_tid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/data/nyt/type_tid.txt -------------------------------------------------------------------------------- /data/stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/data/stopwords.txt -------------------------------------------------------------------------------- /data/tweet/type_tid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/data/tweet/type_tid.txt -------------------------------------------------------------------------------- /data/yelp/type_tid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/data/yelp/type_tid.txt -------------------------------------------------------------------------------- /entity_linking/EntityLinking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/entity_linking/EntityLinking.py -------------------------------------------------------------------------------- /run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/run.sh -------------------------------------------------------------------------------- /src/algorithm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/algorithm.py -------------------------------------------------------------------------------- /src/algorithm.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/algorithm.pyc -------------------------------------------------------------------------------- /src/clustype.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/clustype.py -------------------------------------------------------------------------------- /src/clustype.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/clustype.pyc -------------------------------------------------------------------------------- /src/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/data_model.py -------------------------------------------------------------------------------- /src/data_model.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/data_model.pyc -------------------------------------------------------------------------------- /src/evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/evaluation.py -------------------------------------------------------------------------------- /src/evaluation.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/evaluation.pyc -------------------------------------------------------------------------------- /src/step0-graph_construction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/step0-graph_construction.py -------------------------------------------------------------------------------- /src/step1-entity_recognition.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/INK-USC/ClusType/HEAD/src/step1-entity_recognition.py --------------------------------------------------------------------------------