{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004645544,0.00006287262,0.00005431992,0.00002538348,0.00006063831,0.0001233748,0.0001966929,0.00002329665,0.000009518267],"category_scores_gemma":[0.00002372767,0.00004490218,0.00001526497,0.0003453551,0.00001397807,0.0005360745,0.0000368423,0.00008180064,0.000008551724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009161839,"about_ca_system_score_gemma":0.00003196388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000265046,"about_ca_topic_score_gemma":0.0000135239,"domain_scores_codex":[0.9994858,0.00001382307,0.0000778437,0.0001929652,0.000132764,0.0000968082],"domain_scores_gemma":[0.9997081,0.00002117342,0.0000316461,0.0001447492,0.00004121461,0.00005313007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001622503,0.00002391822,0.0001486025,0.00004042686,0.00000952127,0.0000361624,0.003523368,0.00006216226,0.03737206,0.1024886,0.0004528315,0.8558261],"study_design_scores_gemma":[0.0005666664,0.0002578194,0.0002872305,0.00004760307,0.00001870611,0.00004341155,0.00009548409,0.8183878,0.161609,0.01720268,0.0009055054,0.0005781121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001323363,0.0001230602,0.9885688,0.008219793,0.00001304113,0.00008602461,3.782457e-7,0.001023332,0.0006421736],"genre_scores_gemma":[0.4906017,3.894718e-7,0.5086757,0.0006666044,0.00001618071,0.000002993374,9.094743e-7,0.000003000566,0.00003257176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.855248,"threshold_uncertainty_score":0.1831058,"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."}}