├── .gitignore ├── Analyze Model.ipynb ├── Analyze Text8 Model.ipynb ├── License ├── README.md ├── compile_skipgram_ops.sh ├── evaluation_data ├── MEN │ ├── .DS_Store │ ├── MEN_dataset_lemma_form.dev │ ├── MEN_dataset_lemma_form.test │ ├── MEN_dataset_lemma_form_full │ ├── MEN_dataset_natural_form_full │ ├── agreement │ │ ├── agreement-score.txt │ │ ├── elias-men-ratings.txt │ │ └── marcos-men-ratings.txt │ ├── instructions.txt │ └── licence.txt ├── RL122 │ └── rel122-norms.txt ├── SimLex-999 │ ├── README.txt │ └── SimLex-999.txt ├── ehuang_sim_wcontext │ ├── README.md │ └── SCWS │ │ ├── README │ │ └── ratings.txt ├── entailment_baroni2012 │ ├── README │ ├── matrix_cols │ ├── matrix_rows │ ├── matrix_rows_AN │ ├── matrix_rows_QN │ ├── negative-examples.txtinput │ ├── negativeInput__random1246 │ ├── posInput │ ├── positive-examples.txtinput │ └── q1n__q2n.pairs ├── multiple_datasets │ ├── EN-MC-30.txt │ ├── EN-MEN-TR-3k.txt │ ├── EN-MTurk-287.txt │ ├── EN-MTurk-771.txt │ ├── EN-RG-65.txt │ ├── EN-RW-STANFORD.txt │ ├── EN-WS-353-ALL.txt │ ├── EN-WS-353-REL.txt │ ├── EN-WS-353-SIM.txt │ └── EN-YP-130.txt ├── simverb │ └── data │ │ ├── README.txt │ │ ├── SimVerb-3000-test.txt │ │ ├── SimVerb-3500-ratings.txt │ │ ├── SimVerb-3500-stats.txt │ │ ├── SimVerb-3500.txt │ │ ├── SimVerb-3520-annotator-ratings.csv │ │ └── SimVerb-500-dev.txt └── wordsim353 │ ├── combined.csv │ ├── combined.tab │ ├── instructions.txt │ ├── set1.csv │ ├── set1.tab │ ├── set2.csv │ ├── set2.tab │ └── wordsim353.zip ├── exps ├── train_text8.sh └── train_wac.sh ├── get_text8.sh ├── projectutil.py ├── quantitative_eval.py ├── word2gm_loader.py ├── word2gm_trainer.py ├── word2vec_kernels.cc └── word2vec_ops.cc /.gitignore: -------------------------------------------------------------------------------- 1 | modelfiles 2 | sftp-config.json 3 | *.pyc 4 | text8 5 | .ipynb_checkpoints -------------------------------------------------------------------------------- /Analyze Model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/Analyze Model.ipynb -------------------------------------------------------------------------------- /Analyze Text8 Model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/Analyze Text8 Model.ipynb -------------------------------------------------------------------------------- /License: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/License -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/README.md -------------------------------------------------------------------------------- /compile_skipgram_ops.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/compile_skipgram_ops.sh -------------------------------------------------------------------------------- /evaluation_data/MEN/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/.DS_Store -------------------------------------------------------------------------------- /evaluation_data/MEN/MEN_dataset_lemma_form.dev: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/MEN_dataset_lemma_form.dev -------------------------------------------------------------------------------- /evaluation_data/MEN/MEN_dataset_lemma_form.test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/MEN_dataset_lemma_form.test -------------------------------------------------------------------------------- /evaluation_data/MEN/MEN_dataset_lemma_form_full: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/MEN_dataset_lemma_form_full -------------------------------------------------------------------------------- /evaluation_data/MEN/MEN_dataset_natural_form_full: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/MEN_dataset_natural_form_full -------------------------------------------------------------------------------- /evaluation_data/MEN/agreement/agreement-score.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/agreement/agreement-score.txt -------------------------------------------------------------------------------- /evaluation_data/MEN/agreement/elias-men-ratings.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/agreement/elias-men-ratings.txt -------------------------------------------------------------------------------- /evaluation_data/MEN/agreement/marcos-men-ratings.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/agreement/marcos-men-ratings.txt -------------------------------------------------------------------------------- /evaluation_data/MEN/instructions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/instructions.txt -------------------------------------------------------------------------------- /evaluation_data/MEN/licence.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/MEN/licence.txt -------------------------------------------------------------------------------- /evaluation_data/RL122/rel122-norms.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/RL122/rel122-norms.txt -------------------------------------------------------------------------------- /evaluation_data/SimLex-999/README.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/SimLex-999/README.txt -------------------------------------------------------------------------------- /evaluation_data/SimLex-999/SimLex-999.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/SimLex-999/SimLex-999.txt -------------------------------------------------------------------------------- /evaluation_data/ehuang_sim_wcontext/README.md: -------------------------------------------------------------------------------- 1 | This is downloaded from 2 | http://www-nlp.stanford.edu/~ehhuang/SCWS.zip 3 | -------------------------------------------------------------------------------- /evaluation_data/ehuang_sim_wcontext/SCWS/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/ehuang_sim_wcontext/SCWS/README -------------------------------------------------------------------------------- /evaluation_data/ehuang_sim_wcontext/SCWS/ratings.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/ehuang_sim_wcontext/SCWS/ratings.txt -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/README -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/matrix_cols: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/matrix_cols -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/matrix_rows: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/matrix_rows -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/matrix_rows_AN: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/matrix_rows_AN -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/matrix_rows_QN: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/matrix_rows_QN -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/negative-examples.txtinput: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/negative-examples.txtinput -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/negativeInput__random1246: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/negativeInput__random1246 -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/posInput: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/posInput -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/positive-examples.txtinput: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/positive-examples.txtinput -------------------------------------------------------------------------------- /evaluation_data/entailment_baroni2012/q1n__q2n.pairs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/entailment_baroni2012/q1n__q2n.pairs -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-MC-30.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-MC-30.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-MEN-TR-3k.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-MEN-TR-3k.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-MTurk-287.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-MTurk-287.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-MTurk-771.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-MTurk-771.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-RG-65.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-RG-65.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-RW-STANFORD.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-RW-STANFORD.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-WS-353-ALL.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-WS-353-ALL.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-WS-353-REL.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-WS-353-REL.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-WS-353-SIM.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-WS-353-SIM.txt -------------------------------------------------------------------------------- /evaluation_data/multiple_datasets/EN-YP-130.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/multiple_datasets/EN-YP-130.txt -------------------------------------------------------------------------------- /evaluation_data/simverb/data/README.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/README.txt -------------------------------------------------------------------------------- /evaluation_data/simverb/data/SimVerb-3000-test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/SimVerb-3000-test.txt -------------------------------------------------------------------------------- /evaluation_data/simverb/data/SimVerb-3500-ratings.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/SimVerb-3500-ratings.txt -------------------------------------------------------------------------------- /evaluation_data/simverb/data/SimVerb-3500-stats.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/SimVerb-3500-stats.txt -------------------------------------------------------------------------------- /evaluation_data/simverb/data/SimVerb-3500.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/SimVerb-3500.txt -------------------------------------------------------------------------------- /evaluation_data/simverb/data/SimVerb-3520-annotator-ratings.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/SimVerb-3520-annotator-ratings.csv -------------------------------------------------------------------------------- /evaluation_data/simverb/data/SimVerb-500-dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/simverb/data/SimVerb-500-dev.txt -------------------------------------------------------------------------------- /evaluation_data/wordsim353/combined.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/combined.csv -------------------------------------------------------------------------------- /evaluation_data/wordsim353/combined.tab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/combined.tab -------------------------------------------------------------------------------- /evaluation_data/wordsim353/instructions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/instructions.txt -------------------------------------------------------------------------------- /evaluation_data/wordsim353/set1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/set1.csv -------------------------------------------------------------------------------- /evaluation_data/wordsim353/set1.tab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/set1.tab -------------------------------------------------------------------------------- /evaluation_data/wordsim353/set2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/set2.csv -------------------------------------------------------------------------------- /evaluation_data/wordsim353/set2.tab: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/set2.tab -------------------------------------------------------------------------------- /evaluation_data/wordsim353/wordsim353.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/evaluation_data/wordsim353/wordsim353.zip -------------------------------------------------------------------------------- /exps/train_text8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/exps/train_text8.sh -------------------------------------------------------------------------------- /exps/train_wac.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/exps/train_wac.sh -------------------------------------------------------------------------------- /get_text8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/get_text8.sh -------------------------------------------------------------------------------- /projectutil.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/projectutil.py -------------------------------------------------------------------------------- /quantitative_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/quantitative_eval.py -------------------------------------------------------------------------------- /word2gm_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/word2gm_loader.py -------------------------------------------------------------------------------- /word2gm_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/word2gm_trainer.py -------------------------------------------------------------------------------- /word2vec_kernels.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/word2vec_kernels.cc -------------------------------------------------------------------------------- /word2vec_ops.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/benathi/word2gm/HEAD/word2vec_ops.cc --------------------------------------------------------------------------------