{"id":"W2109163800","doi":"10.1145/1187415.1187417","title":"A statistical model for near-synonym choice","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Synonym (taxonomy); Artificial intelligence; Natural language processing; Task (project management); Context (archaeology); Machine translation; Thesaurus; Mutual information; Information retrieval; Machine learning","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":[0.000425366,0.000192074,0.0001761294,0.0001358429,0.0004433503,0.0003867654,0.0005717867,0.0001192087,0.00001258368],"category_scores_gemma":[0.0001676092,0.0001694326,0.00004658852,0.0003140589,0.00008464247,0.0005752994,0.00002214741,0.0002918141,0.000002838231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004174876,"about_ca_system_score_gemma":0.00010034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004433204,"about_ca_topic_score_gemma":0.00009970817,"domain_scores_codex":[0.9986345,0.00001388799,0.0002354342,0.0004556658,0.0002415595,0.0004189626],"domain_scores_gemma":[0.9989464,0.0003163858,0.00007196594,0.0004111353,0.000102918,0.0001511936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003004011,0.00005880863,0.000008453841,0.00009296165,0.000006819258,0.00002052686,0.001549339,0.00003131428,0.001602214,0.0005060942,0.00002895814,0.9960645],"study_design_scores_gemma":[0.001024877,0.0002427703,0.00008452106,0.0002061457,0.00005419638,0.0001738969,0.0003481439,0.91281,0.06134216,0.02232167,0.0006835413,0.0007080326],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003665246,0.002726696,0.9921808,0.0004304935,0.00004811417,0.0002346301,0.00001777603,0.0005797393,0.0001165606],"genre_scores_gemma":[0.4069453,0.000004842898,0.5922379,0.0004959788,0.00002736153,0.00001753757,0.000003162378,0.00001428731,0.0002536242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9953564,"threshold_uncertainty_score":0.6909263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01971804255985616,"score_gpt":0.3185797563200914,"score_spread":0.2988617137602353,"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."}}