{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001208638,0.001459613,0.0008800334,0.002507294,0.0007055784,0.001582668,0.003068325,0.001707703,0.005275265],"category_scores_gemma":[0.00579948,0.000447408,0.001326062,0.002428247,0.0007943772,0.004424379,0.002678314,0.002919498,0.001861123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001196078,"about_ca_system_score_gemma":0.002224455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01143339,"about_ca_topic_score_gemma":0.02194412,"domain_scores_codex":[0.9992292,0.0001665913,0.00005021163,0.0002784542,0.0002128493,0.00006265598],"domain_scores_gemma":[0.9978472,0.001052517,0.0001611962,0.0005415601,0.000320444,0.00007704369],"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":[0.0003436285,0.0002669923,0.003598909,0.0003667086,0.0001407777,0.0001217501,0.0005670011,0.04677072,0.007179987,0.03035996,0.03338489,0.8768986],"study_design_scores_gemma":[0.00005916435,0.00008663153,0.0006558197,0.00005392105,0.00004142934,0.00007541444,0.0001700231,0.9282738,0.006521735,0.05022177,0.01380387,0.00003636316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02277019,0.0004891489,0.9582475,0.000537169,0.0001546927,0.0001629616,0.002013507,0.01367687,0.001947963],"genre_scores_gemma":[0.2493753,0.0005567324,0.7326714,0.0004806325,0.0001918075,0.0003235087,0.01007096,0.001058517,0.005271175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01143339,"threshold_uncertainty_score":0.02273369,"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."}}