{"id":"W2965233127","doi":"10.24963/ijcai.2019/731","title":"Modeling Noisy Hierarchical Types in Fine-Grained Entity Typing: A Content-Based Weighting Approach","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Computer science; Weighting; Artificial intelligence; Benchmark (surveying); Embedding; Schema (genetic algorithms); Process (computing); Noisy data; Sentence; Set (abstract data type); Data mining; Machine learning; Natural language processing","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":[0.003412182,0.001135866,0.001355433,0.003043056,0.0007987783,0.001411776,0.002784884,0.001941722,0.00139505],"category_scores_gemma":[0.0123001,0.0007308327,0.001232115,0.003803658,0.0008421323,0.005571259,0.002169661,0.002306035,0.001096067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008825252,"about_ca_system_score_gemma":0.0009036805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004013664,"about_ca_topic_score_gemma":0.009351993,"domain_scores_codex":[0.9981613,0.0006013972,0.0001504636,0.0005814008,0.0003575173,0.0001478113],"domain_scores_gemma":[0.9938893,0.00316378,0.0006486718,0.001167666,0.0009322169,0.0001983042],"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":[0.0005362451,0.000582065,0.0193784,0.000514654,0.0002839238,0.000536722,0.001833786,0.2689084,0.02809126,0.05076931,0.01117433,0.6173908],"study_design_scores_gemma":[0.00001351425,0.00004798182,0.001273969,0.00002908727,0.00004956223,0.0001356764,0.0001073295,0.9617507,0.003985828,0.02989787,0.002681179,0.00002736731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02116673,0.0002241852,0.9772527,0.000104098,0.00003853175,0.00006784566,0.0001903946,0.0005339519,0.0004215951],"genre_scores_gemma":[0.4504804,0.0004900616,0.5398435,0.0002713452,0.0001798486,0.0003459086,0.002065034,0.0005889984,0.005734893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004013664,"threshold_uncertainty_score":0.0180456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04582902879619467,"score_gpt":0.2401210719933347,"score_spread":0.19429204319714,"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."}}