{"id":"W2889675133","doi":"10.18653/v1/d18-1121","title":"Put It Back: Entity Typing with Language Model Enhancement","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Tsinghua University; National Natural Science Foundation of China; National Key Research and Development Program of China; China Association for Science and Technology","keywords":"Computer science; Natural language processing; Language model; Artificial intelligence; Benchmark (surveying); Entity linking; Context (archaeology); Code (set theory); Source code; Typing; Baseline (sea); Information retrieval; Programming language; Speech recognition","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":[0.0001296176,0.00007478778,0.00007096631,0.00003200041,0.00006520118,0.0000874569,0.0004316225,0.00001802298,0.0002664604],"category_scores_gemma":[0.000004649916,0.00005716669,0.00001668733,0.00009997762,0.00002387537,0.0003022801,0.0002019598,0.00004882316,0.0004332889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002868576,"about_ca_system_score_gemma":0.00004831666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000772554,"about_ca_topic_score_gemma":0.0001497939,"domain_scores_codex":[0.9992634,0.00001072094,0.0001032957,0.0002761939,0.0001480667,0.0001982872],"domain_scores_gemma":[0.9993687,0.000007650881,0.00002863552,0.0004901843,0.00005450075,0.00005038961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005279834,0.0004671324,0.001412128,0.0001420551,0.0001628978,0.00004811622,0.03203426,0.01528774,0.04236362,0.6566493,0.02383398,0.227546],"study_design_scores_gemma":[0.0001401811,0.00003995139,0.00001424403,0.00001594366,0.000001759729,0.000003110655,0.00004384944,0.9858801,0.01234347,0.0005414573,0.0008728683,0.0001030895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03772345,0.00001294276,0.8976858,0.0006230916,0.0000931191,0.00006855475,1.662373e-7,0.00007512442,0.06371775],"genre_scores_gemma":[0.6308297,0.00000140704,0.3602425,0.000888659,0.00006264308,0.000002991413,3.093056e-7,0.000003402615,0.007968422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9705923,"threshold_uncertainty_score":0.5569196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02520113987968561,"score_gpt":0.264591339022488,"score_spread":0.2393901991428024,"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."}}