{"id":"W2250484029","doi":"10.3115/v1/p14-2087","title":"Applying a Naive Bayes Similarity Measure to Word Sense Disambiguation","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Word-sense disambiguation; Naive Bayes classifier; Bayes' theorem; Computer science; Word (group theory); Artificial intelligence; Similarity (geometry); Simple (philosophy); Natural language processing; Measure (data warehouse); Semantic similarity; Mathematics; Bayesian probability; Data mining; WordNet","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":[0.0005308904,0.0001210645,0.0001220161,0.00009703058,0.0001253056,0.0002343245,0.000470405,0.00006819399,0.000009546363],"category_scores_gemma":[0.0004029713,0.00009845685,0.00003678564,0.0004098017,0.00001549625,0.0004264435,0.0002664164,0.0001412527,0.00003884307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004627498,"about_ca_system_score_gemma":0.00002394979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006486823,"about_ca_topic_score_gemma":0.00004125368,"domain_scores_codex":[0.9988874,0.00007712954,0.00013903,0.0003599594,0.000323625,0.0002128474],"domain_scores_gemma":[0.9991782,0.00009100042,0.00004803631,0.0004487041,0.0001389168,0.00009508212],"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":[0.000007939498,0.00003078011,0.0002131244,0.00002270742,0.000006693258,0.000006424176,0.0008971977,0.00001574065,0.01213373,0.08667314,0.002867955,0.8971246],"study_design_scores_gemma":[0.0006486253,0.0002924831,0.001551693,0.0003946539,0.00002651707,0.00007197697,0.0001289568,0.2268903,0.3204761,0.4263227,0.0215233,0.00167268],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001924929,0.00009208181,0.9924632,0.001995066,0.0000932141,0.00030261,4.665345e-7,0.001127447,0.002001004],"genre_scores_gemma":[0.5096514,4.503698e-7,0.4885931,0.00154971,0.0000401785,0.00004682678,8.03716e-7,0.000004972425,0.0001126514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8954519,"threshold_uncertainty_score":0.4014954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01600109139405482,"score_gpt":0.2691007630015634,"score_spread":0.2530996716075086,"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."}}