{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004828324,0.0001479691,0.0002263341,0.0001786067,0.00005086332,0.0001189751,0.0006911728,0.000084534,0.00003178808],"category_scores_gemma":[0.00007424605,0.0001286275,0.00007628776,0.000302634,0.000014709,0.0002972248,0.0002303739,0.0002715834,0.00006694278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005476534,"about_ca_system_score_gemma":0.0001009041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002992378,"about_ca_topic_score_gemma":0.00006570661,"domain_scores_codex":[0.9984412,0.00007411795,0.0003324537,0.0005481939,0.0002327867,0.0003712389],"domain_scores_gemma":[0.9991713,0.00007399364,0.00004110365,0.0005708104,0.00006206922,0.00008077187],"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":[0.00005319615,0.0003999705,0.02476387,0.0001768826,0.0000338482,0.00001512687,0.001190403,0.458127,0.006246164,0.4827101,0.00002995484,0.02625358],"study_design_scores_gemma":[0.0006396898,0.00001955121,0.0001493057,0.00002974717,0.000001810823,0.000002169815,0.00003092001,0.9975058,0.000292611,0.001117353,0.00004081005,0.0001702415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3337744,0.00003915475,0.6610008,0.0004563054,0.0001312241,0.0001572645,2.713898e-7,0.000128263,0.004312266],"genre_scores_gemma":[0.7599823,5.179402e-7,0.2393228,0.0002728458,0.00003584215,0.000009423184,0.000002633123,0.000007910242,0.0003656976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5393788,"threshold_uncertainty_score":0.5245278,"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."}}