{"id":"W2806477841","doi":"10.3390/info9060133","title":"A Machine Learning Filter for the Slot Filling Task","year":2018,"lang":"en","type":"article","venue":"Information","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Computer science; Classifier (UML); Artificial intelligence; USable; Relationship extraction; Natural language processing; Precision and recall; Filter (signal processing); Information extraction; Machine learning; Speech recognition; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002715094,0.00004231181,0.00003475836,0.00003551508,0.0002186581,0.0001577177,0.0002829748,0.00002056115,0.00001134845],"category_scores_gemma":[0.00008443431,0.00002883379,0.00002268709,0.00007471409,0.00001139913,0.001176418,0.00006941608,0.00006039184,0.0001071174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001344737,"about_ca_system_score_gemma":0.00001315885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002392285,"about_ca_topic_score_gemma":0.000003344298,"domain_scores_codex":[0.9995895,0.00000855468,0.0001425968,0.00005145422,0.0001007003,0.0001072118],"domain_scores_gemma":[0.999577,0.00008021894,0.00006701751,0.0001794935,0.00008154521,0.00001472922],"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":[0.00001074822,0.000004602384,0.0001466018,0.00002569991,0.00001397012,1.032971e-7,0.01367942,0.01747822,0.0001583105,0.06948881,0.001451849,0.8975416],"study_design_scores_gemma":[0.00009886552,0.00002447329,0.00008115627,0.00000488848,0.000001254759,0.000001911242,0.0000215023,0.833875,0.0002850787,0.0005661269,0.1650045,0.00003524352],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001458833,0.00002003655,0.9941452,0.0008442045,0.0003017948,0.0001274785,0.000001248441,0.00008656202,0.00301466],"genre_scores_gemma":[0.9446043,0.000003171168,0.05394121,0.001037912,0.0001839099,0.0000238322,0.000007803271,0.000002347861,0.0001955583],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9431454,"threshold_uncertainty_score":0.1681764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02177142452139717,"score_gpt":0.240311881795766,"score_spread":0.2185404572743688,"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."}}