{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001619438,0.001638541,0.001056161,0.001952822,0.0005481688,0.001807887,0.00348899,0.001979381,0.003844525],"category_scores_gemma":[0.008467794,0.0008509309,0.001598667,0.001977759,0.000810282,0.006360384,0.002909289,0.003685546,0.002657779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001297045,"about_ca_system_score_gemma":0.001651878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007042446,"about_ca_topic_score_gemma":0.0103277,"domain_scores_codex":[0.9989231,0.0003148703,0.00008170235,0.0004336472,0.0001429554,0.0001037442],"domain_scores_gemma":[0.9974995,0.001312425,0.0001670459,0.0005458388,0.0003765058,0.00009871783],"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":[0.000286008,0.0003052568,0.00212704,0.0003351754,0.000237346,0.0002602575,0.0002888322,0.4736743,0.004539481,0.02031758,0.02366561,0.473963],"study_design_scores_gemma":[0.00001191673,0.0000245536,0.0001192538,0.00002077657,0.00002178006,0.00003280412,0.00001972442,0.9861498,0.001178379,0.01047352,0.001935419,0.00001213431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01734339,0.001019423,0.9703542,0.0007331039,0.0001410118,0.0001401233,0.001671095,0.006764164,0.001833591],"genre_scores_gemma":[0.4433835,0.001413751,0.5243282,0.001041009,0.0002326722,0.0008719896,0.01626695,0.0009986747,0.01146322],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007042446,"threshold_uncertainty_score":0.01400292,"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."}}