{"id":"W4389519419","doi":"10.18653/v1/2023.emnlp-main.37","title":"Knowledge Graph Compression Enhances Diverse Commonsense Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Commonsense knowledge; Computer science; Commonsense reasoning; Knowledge graph; Artificial intelligence; Graph; Context (archaeology); Task (project management); Natural language processing; Theoretical computer science; Machine learning; Knowledge-based systems","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":[0.001022049,0.0007509835,0.0005973655,0.001255255,0.0004410149,0.0009465173,0.001353953,0.001134452,0.003076352],"category_scores_gemma":[0.007940157,0.0002968521,0.0008855775,0.0009856391,0.0009047877,0.002758052,0.001743439,0.001300733,0.0005034769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008788154,"about_ca_system_score_gemma":0.0009294978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002858243,"about_ca_topic_score_gemma":0.004724885,"domain_scores_codex":[0.9993641,0.0001958952,0.0000259884,0.0001821796,0.0001801861,0.00005181137],"domain_scores_gemma":[0.9959111,0.003028187,0.0001473931,0.0005276086,0.000281965,0.0001038307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002304873,0.0003027539,0.002646049,0.0002449666,0.0000729005,0.0005645094,0.0005690883,0.6609557,0.01225332,0.05928527,0.004816357,0.2580585],"study_design_scores_gemma":[0.00001766693,0.00002120476,0.0002045815,0.00001270202,0.00001668965,0.00006546973,0.00003760324,0.9608444,0.003340952,0.03392073,0.001511069,0.000006893243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1079744,0.0004236429,0.8803434,0.0009068199,0.0000514693,0.0001886074,0.0005345918,0.002538972,0.007038186],"genre_scores_gemma":[0.7376235,0.0003120872,0.2568256,0.0003023612,0.00006036254,0.0001912749,0.001704891,0.0003464987,0.002633453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003076352,"threshold_uncertainty_score":0.0102914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09308819212558869,"score_gpt":0.3087466646658838,"score_spread":0.2156584725402951,"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."}}