{"id":"W3151929433","doi":"10.1162/tacl_a_00360","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":602,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; HEC Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Kepler; Embedding; Benchmark (surveying); Language model; Representation (politics); Natural language processing; Construct (python library); ENCODE; Artificial intelligence; Programming language","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":[0.0002917282,0.00008029443,0.0001368116,0.00005438758,0.0002470258,0.0000615193,0.0001958445,0.00006295403,9.218451e-7],"category_scores_gemma":[0.001681528,0.00008080307,0.0001244867,0.0002018253,0.00001426938,0.00006531322,0.00002143575,0.00007029317,2.703899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056683,"about_ca_system_score_gemma":0.0002082442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007195771,"about_ca_topic_score_gemma":0.00002280106,"domain_scores_codex":[0.999116,0.00004474204,0.0002995125,0.0002196717,0.000193905,0.000126147],"domain_scores_gemma":[0.9973218,0.001111844,0.0002167669,0.0001934551,0.001125724,0.0000303466],"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":[0.000008329846,0.00005420297,0.00008059449,0.00005025341,0.00005542739,6.754033e-8,0.002822822,0.897187,0.0001539181,0.09796598,0.00007959981,0.001541781],"study_design_scores_gemma":[0.0005669486,0.00001346673,0.0002882071,0.00001800716,0.00005112718,0.000001026585,0.00009356833,0.9495437,0.0005865793,0.04854103,0.000218591,0.00007772139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00263066,0.0000544465,0.9956169,0.0004446331,0.0004955236,0.0003085322,0.0001145145,0.00005237757,0.0002824734],"genre_scores_gemma":[0.6736804,0.000002287419,0.3246725,0.00003791565,0.00007545188,0.0000279314,0.00002745661,0.000007230752,0.00146884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6710497,"threshold_uncertainty_score":0.3295054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03147363115435537,"score_gpt":0.3240863137469095,"score_spread":0.2926126825925541,"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."}}