{"id":"W3153765506","doi":"10.18653/v1/2021.eacl-main.263","title":"DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Alberta Machine Intelligence Institute","keywords":"Computer science; Class (philosophy); Natural language processing; Artificial intelligence; Semantic memory; Support vector machine; Information retrieval; Psychology","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":[0.00016319,0.0001929718,0.0002593736,0.0000647753,0.0001212468,0.0003124292,0.0006295493,0.00005364052,0.00007797472],"category_scores_gemma":[0.00005426651,0.0001507139,0.00007145722,0.0004692749,0.00003380935,0.0004105309,0.0004645744,0.000183641,0.0001539274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005962685,"about_ca_system_score_gemma":0.0001911077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005708491,"about_ca_topic_score_gemma":0.0003781938,"domain_scores_codex":[0.9983808,0.00006737075,0.0002583925,0.0006463792,0.0002318608,0.0004151322],"domain_scores_gemma":[0.9986461,0.0001228332,0.00005713226,0.0008988695,0.0001439948,0.0001310825],"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":[0.00004052199,0.000984117,0.01821768,0.0009360911,0.0004270948,0.001178812,0.01264149,0.007939129,0.01192157,0.8619545,0.001862865,0.08189615],"study_design_scores_gemma":[0.0003133918,0.00004542667,0.0007108143,0.0002183062,0.00002204939,0.0001004528,0.0001104753,0.9903077,0.003917003,0.001386963,0.002549882,0.0003174761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04368719,0.0003663303,0.9395261,0.0008740702,0.0004437871,0.0001036651,7.106065e-7,0.000289967,0.01470811],"genre_scores_gemma":[0.9327589,0.00001000539,0.06211437,0.000184753,0.0000854221,0.00001176997,0.000001917519,0.00001699386,0.004815819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9823686,"threshold_uncertainty_score":0.6145933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01536453489862841,"score_gpt":0.2392703730202656,"score_spread":0.2239058381216372,"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."}}