{"id":"W1975422446","doi":"10.1145/1076034.1076086","title":"Integrating word relationships into language models","year":2005,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"WordNet; Computer science; Dependency (UML); Language model; Natural language processing; Word (group theory); Artificial intelligence; Independence (probability theory); Information retrieval; 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":[0.0002629099,0.00006355369,0.00005989673,0.00005773356,0.0001028535,0.00009044372,0.0004138878,0.00003637123,0.00002511892],"category_scores_gemma":[0.00004956621,0.00005351441,0.00002589455,0.0001509542,0.000007585735,0.000782603,0.0001351117,0.0001665653,0.000094925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004119111,"about_ca_system_score_gemma":0.00002359806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043277,"about_ca_topic_score_gemma":0.0002984568,"domain_scores_codex":[0.9993509,0.0000373487,0.0001538706,0.0002007964,0.0001262809,0.0001308244],"domain_scores_gemma":[0.9994478,0.0000681735,0.00002742904,0.0003827602,0.00002569544,0.0000481266],"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":[2.88413e-7,0.00000907406,0.00011913,0.00000187244,0.000002273133,0.000001437259,0.00882592,0.01660341,0.0002115942,0.7004026,0.0002425913,0.2735798],"study_design_scores_gemma":[0.00005482085,0.000002808425,0.00003371434,0.000007318058,7.265616e-7,0.00000283265,0.0003257144,0.9736692,0.0003679995,0.02494851,0.0005140641,0.00007232959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02955408,0.00009634267,0.9262456,0.002232174,0.00005890425,0.00004533023,5.598234e-8,0.000261454,0.0415061],"genre_scores_gemma":[0.5368618,7.139161e-7,0.4617437,0.000210299,0.0000534053,0.000002751872,2.95206e-7,0.000002314711,0.001124693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9570658,"threshold_uncertainty_score":0.2182254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04566723421462487,"score_gpt":0.2723542965639025,"score_spread":0.2266870623492776,"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."}}