{"id":"W2121274514","doi":"10.3115/1218955.1218992","title":"Unsupervised sense disambiguation using bilingual probabilistic models","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Science Foundation","keywords":"Computer science; Probabilistic logic; Natural language processing; Artificial intelligence; Language model; Task (project management); Statistical model; Word (group theory); Word-sense disambiguation; Unsupervised learning; Latent variable; Machine learning; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003186201,0.001287756,0.001221754,0.00265217,0.001334011,0.002012401,0.002379617,0.00131488,0.003010863],"category_scores_gemma":[0.009911559,0.001127353,0.001937772,0.003159452,0.001352041,0.005017878,0.003140832,0.002229566,0.001930428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001042206,"about_ca_system_score_gemma":0.002213859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003923506,"about_ca_topic_score_gemma":0.008682734,"domain_scores_codex":[0.9971917,0.001199874,0.0001533581,0.0007431071,0.0005887031,0.0001232703],"domain_scores_gemma":[0.9955574,0.00252318,0.0004360474,0.0007807927,0.0005490583,0.0001536758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004504126,0.0005354575,0.005934568,0.0004400353,0.0004825372,0.000702617,0.001079228,0.3912752,0.009430074,0.1959107,0.01743024,0.3763289],"study_design_scores_gemma":[0.00004329081,0.00003262693,0.0005692926,0.00002223631,0.00004197443,0.0002082135,0.00005628376,0.841668,0.001988529,0.1499077,0.005416038,0.00004587079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008708715,0.0002416061,0.9872132,0.0002940373,0.00004605899,0.00005863308,0.0002750388,0.001113172,0.002049496],"genre_scores_gemma":[0.3032415,0.0006738852,0.6869732,0.0004904472,0.0002326691,0.0005170648,0.002585835,0.0005106116,0.004774724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003923506,"threshold_uncertainty_score":0.01685041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04102658423590184,"score_gpt":0.2908114587039068,"score_spread":0.249784874468005,"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."}}