{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001600528,0.001163371,0.001135334,0.002109782,0.00110984,0.001358232,0.001411179,0.001425327,0.003955182],"category_scores_gemma":[0.006129113,0.0005741426,0.000857336,0.002752352,0.0005516467,0.003817637,0.001332912,0.002171028,0.006163536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000838376,"about_ca_system_score_gemma":0.001112447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007010773,"about_ca_topic_score_gemma":0.01741138,"domain_scores_codex":[0.9988678,0.0005641904,0.00007881922,0.0002230075,0.0001923505,0.00007393795],"domain_scores_gemma":[0.9972017,0.001611735,0.0001812106,0.0004745093,0.0004403621,0.00009062875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001047829,0.0004620215,0.005870433,0.0003723222,0.0003117976,0.0004635839,0.0004471669,0.349241,0.0111684,0.04011371,0.03297758,0.5575242],"study_design_scores_gemma":[0.00001053471,0.00001673112,0.0002618087,0.000009693505,0.000009765472,0.00003835213,0.00001927644,0.9790208,0.0008023055,0.0184483,0.001347182,0.00001512722],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03361065,0.001680763,0.9504364,0.0006745874,0.0002703921,0.0001168157,0.002012748,0.007550416,0.003647167],"genre_scores_gemma":[0.5385631,0.001356927,0.4436825,0.0005502943,0.0004936825,0.0004285708,0.005748376,0.0009567511,0.008219905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007010773,"threshold_uncertainty_score":0.01393998,"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."}}