{"id":"W2806319975","doi":"10.63317/2zjrem3tbunr","title":"Transforming Wikipedia into a Large-Scale Fine-Grained Entity Type Corpus","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Scale (ratio); Information retrieval; Artificial intelligence; Type (biology); World Wide Web; Geology; Geography; Cartography","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":[0.0009555981,0.0007270912,0.0007474394,0.004966089,0.001185773,0.002030715,0.0009559587,0.0008310117,0.007413754],"category_scores_gemma":[0.007615709,0.0007415264,0.001023311,0.004921018,0.0005276738,0.003108339,0.002389849,0.002034432,0.006460927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006965178,"about_ca_system_score_gemma":0.002162687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00804121,"about_ca_topic_score_gemma":0.01848542,"domain_scores_codex":[0.9988034,0.0002001528,0.0001506561,0.0004427159,0.0003190959,0.00008401739],"domain_scores_gemma":[0.9949147,0.002080177,0.0002098403,0.001061709,0.001586999,0.000146579],"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":[0.0009183314,0.0008574594,0.01240301,0.002990197,0.0004603107,0.004253244,0.002540532,0.02836058,0.1499872,0.0381656,0.2374166,0.521647],"study_design_scores_gemma":[0.0001629884,0.0002297142,0.02334255,0.0003507721,0.0004509515,0.002993086,0.002544877,0.2651871,0.1306087,0.07397275,0.4998486,0.0003078332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1231108,0.001347396,0.6419531,0.002154643,0.002183723,0.0009317891,0.1585448,0.04619142,0.0235823],"genre_scores_gemma":[0.194067,0.0006925475,0.5841897,0.0003625459,0.0002597522,0.0005007365,0.208775,0.003196974,0.007955692],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00804121,"threshold_uncertainty_score":0.02480143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009159296413010809,"score_gpt":0.2687434385094682,"score_spread":0.2595841420964574,"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."}}