{"id":"W3099330995","doi":"10.18653/v1/2020.emnlp-main.332","title":"Improving Word Sense Disambiguation with Translations","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Word-sense disambiguation; Computer science; Natural language processing; Word (group theory); SemEval; Artificial intelligence; Sense (electronics); Linguistics; WordNet; Engineering; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003166652,0.002155144,0.001732297,0.004695137,0.001466035,0.002381383,0.001407907,0.001016292,0.003325542],"category_scores_gemma":[0.009990274,0.0007870913,0.001238947,0.0051769,0.00102236,0.004179119,0.003408176,0.00129926,0.004542296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004984461,"about_ca_system_score_gemma":0.001893691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002727291,"about_ca_topic_score_gemma":0.004069931,"domain_scores_codex":[0.9961638,0.001328241,0.000515136,0.001074551,0.0007607468,0.0001575163],"domain_scores_gemma":[0.996148,0.001338281,0.0003609166,0.0009060515,0.001144538,0.000102318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005858816,0.0003861733,0.006337281,0.001109574,0.0003771386,0.0008141398,0.001369736,0.03727478,0.1123183,0.01671505,0.01515492,0.807557],"study_design_scores_gemma":[0.0002650326,0.0004800501,0.005225324,0.0001639842,0.0005044045,0.001517695,0.001732696,0.5987723,0.2830951,0.04825371,0.05975684,0.0002329871],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09415999,0.00201241,0.8829782,0.000415909,0.0004024026,0.0002186077,0.0008390879,0.01376597,0.005207435],"genre_scores_gemma":[0.2476559,0.0009186256,0.7433164,0.0003101138,0.0001212767,0.0001189839,0.0032191,0.001073177,0.003266422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004695137,"threshold_uncertainty_score":0.016747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01577025542673025,"score_gpt":0.2411865839604292,"score_spread":0.225416328533699,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}