{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001621002,0.00006669274,0.00007122867,0.0001077394,0.0001594137,0.00007655894,0.0003423775,0.00003181258,0.00002162671],"category_scores_gemma":[0.00001113508,0.00005540539,0.00003273512,0.000369298,0.00001635274,0.0002416467,0.0002897785,0.00005274863,0.0004347195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009995649,"about_ca_system_score_gemma":0.00001745545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003655885,"about_ca_topic_score_gemma":0.00008659646,"domain_scores_codex":[0.9993182,0.00005779335,0.0001169494,0.0002323927,0.0001259406,0.0001487675],"domain_scores_gemma":[0.9994965,0.00004448516,0.0000255431,0.0003449255,0.00004015524,0.00004839937],"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":[0.000005490349,0.0001463728,0.001288411,0.00003605899,0.00002794696,0.00005021162,0.008721952,0.005776921,0.18834,0.2031683,0.1708138,0.4216246],"study_design_scores_gemma":[0.0001367166,0.00001459608,0.0007291131,0.000009937429,0.000001581263,0.000002101396,0.0000773787,0.9746318,0.01873502,0.001869929,0.003682854,0.0001089706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2716438,0.00005132776,0.7190181,0.0006240336,0.0008143279,0.00007329322,4.933751e-7,0.0005603021,0.007214284],"genre_scores_gemma":[0.9801271,0.0000240689,0.01773584,0.0001048526,0.0001123572,0.000006330625,0.000004315582,0.000003383683,0.001881734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9688549,"threshold_uncertainty_score":0.5587585,"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."}}