{"id":"W2131526828","doi":"10.1162/coli.2006.32.2.223","title":"Building and Using a Lexical Knowledge Base of Near-Synonym Differences","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Ottawa; University of Pennsylvania","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Knowledge base; Artificial intelligence; Mistake; Natural language; Bilingual dictionary; Word (group theory); Linguistics","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":[0.0001873533,0.0001051655,0.0001506744,0.00007838413,0.0001284155,0.0001265195,0.0002376,0.00005187832,0.000002014909],"category_scores_gemma":[0.0006222121,0.00009798116,0.00002836486,0.0002225359,0.0001388596,0.00004859341,0.0002032773,0.0001039154,7.415676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002682572,"about_ca_system_score_gemma":0.0001421913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005455599,"about_ca_topic_score_gemma":0.00000353382,"domain_scores_codex":[0.999167,0.00004005439,0.0002383644,0.000221521,0.0001863025,0.000146779],"domain_scores_gemma":[0.9989266,0.0003831478,0.0001132436,0.0001136755,0.0004181362,0.00004516936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002894054,0.00006380349,0.001814975,0.00006159167,0.000005387628,0.0000148616,0.00009996306,0.002691872,0.0004753615,0.9900975,0.00007070715,0.004601146],"study_design_scores_gemma":[0.00007910151,0.00001941639,0.001357748,0.00005886851,0.000005908827,0.00001274383,0.000001291492,0.6732213,0.0007140487,0.3242748,0.0001582387,0.00009650443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04440339,0.001545259,0.9533795,0.00003494023,0.000185562,0.00005135997,0.00000537647,0.0001328717,0.0002617146],"genre_scores_gemma":[0.4995616,4.482928e-7,0.5002994,0.00001714845,0.000108972,5.894105e-7,0.000001860443,0.000003449056,0.000006517294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6705295,"threshold_uncertainty_score":0.3995556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02656855028045379,"score_gpt":0.3117453974176719,"score_spread":0.2851768471372181,"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."}}