{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001980274,0.000128978,0.0001129471,0.00009791656,0.0001056113,0.00018125,0.000375252,0.00006829148,0.000004386359],"category_scores_gemma":[0.00009040422,0.0001042098,0.00004112364,0.000415642,0.00003997107,0.0009111852,0.0001673399,0.000111307,0.000006941346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001525295,"about_ca_system_score_gemma":0.0002335411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001993217,"about_ca_topic_score_gemma":0.00001665332,"domain_scores_codex":[0.9989486,0.00002620064,0.0001919046,0.0003537701,0.0002586409,0.0002208219],"domain_scores_gemma":[0.9993013,0.00003001546,0.00005146052,0.0004241165,0.0001320941,0.00006102385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000663805,0.0001157281,0.000007100398,0.0000485581,0.000007781549,0.00005490928,0.002603817,0.03472077,0.02958175,0.915081,0.000009524046,0.01776242],"study_design_scores_gemma":[0.0001742381,0.00002548383,0.000002619003,0.00003801219,0.000004087625,0.00004267771,0.00001400903,0.4751754,0.02754195,0.4968264,0.00000443392,0.0001507441],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07748052,0.0002260483,0.920223,0.0004399354,0.00007655745,0.0001860199,5.927144e-7,0.001017335,0.000349995],"genre_scores_gemma":[0.4956045,9.645747e-7,0.5041446,0.0001959917,0.00002149221,0.000002421484,0.000001178614,0.000005987721,0.0000227816],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4404546,"threshold_uncertainty_score":0.4249552,"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."}}