{"id":"W1740463855","doi":"","title":"Web-scale N-gram models for lexical disambiguation","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Context (archaeology); n-gram; Artificial intelligence; Selection (genetic algorithm); Spelling; Scale (ratio); Information retrieval; Language model; 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":[0.0001390821,0.00007635733,0.00008149017,0.00004771545,0.00006727523,0.0001366428,0.0004849143,0.00006057807,0.000003594261],"category_scores_gemma":[0.00002117062,0.00005939412,0.00004694747,0.000158205,0.00001288513,0.0006769651,0.00004490039,0.00006325314,0.00000457413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002313929,"about_ca_system_score_gemma":0.00002786589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006014776,"about_ca_topic_score_gemma":0.000005379467,"domain_scores_codex":[0.999332,0.00001057384,0.0001150448,0.0002302591,0.0001440713,0.0001681131],"domain_scores_gemma":[0.9995764,0.00002845407,0.00002986692,0.0002539977,0.00006587277,0.00004538722],"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":[0.00000438309,0.00004531713,0.000002769141,0.000004193459,0.000001098437,6.73547e-7,0.0001092516,0.00002784851,0.004138706,0.6714736,0.003183107,0.3210091],"study_design_scores_gemma":[0.00008771883,0.00006844221,0.00001328211,0.000005546093,0.000001267603,0.000002553023,0.000001731397,0.424888,0.0159289,0.5586356,0.0002918731,0.00007515054],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005928514,0.000195993,0.9913506,0.004203754,0.00005141499,0.0001689319,8.048306e-7,0.001007132,0.002428498],"genre_scores_gemma":[0.4396168,0.000001736993,0.5592079,0.0007813037,0.00002826939,0.000009953453,0.000002014545,0.000002164412,0.0003497763],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.439024,"threshold_uncertainty_score":0.2422022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02128184406940061,"score_gpt":0.2996087455678126,"score_spread":0.278326901498412,"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."}}