{"id":"W3115808866","doi":"10.18653/v1/2020.coling-main.58","title":"TIMBERT: Toponym Identifier For The Medical Domain Based on BERT","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentence; Identifier; Domain (mathematical analysis); Natural language processing; Set (abstract data type); Artificial intelligence; Task (project management); Test set; Identification (biology); Process (computing); Named-entity recognition; Programming language","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":[0.0003570835,0.00006802911,0.00007580702,0.00001393573,0.00008953489,0.00008878935,0.000919336,0.00004511667,0.000327322],"category_scores_gemma":[0.0001804812,0.00004069834,0.000064829,0.000102779,0.00001877265,0.00007551358,0.0001296496,0.000094348,0.00008984607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001075633,"about_ca_system_score_gemma":0.00006779598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001579233,"about_ca_topic_score_gemma":0.00001440076,"domain_scores_codex":[0.998996,0.00002852972,0.0001368334,0.0002676088,0.0004115035,0.000159571],"domain_scores_gemma":[0.9990233,0.0004240994,0.00001966196,0.0003862366,0.00002377184,0.0001229169],"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":[0.00004504391,0.00009443895,0.000164202,0.00004019272,0.00003761609,0.0000490199,0.001483039,0.00504976,0.0002606203,0.7067534,0.1129185,0.1731041],"study_design_scores_gemma":[0.000268064,0.000031774,0.00004029939,0.000005272033,0.000001894221,0.000001280621,0.00001033732,0.9456571,0.0003311391,0.00245418,0.05113948,0.00005922151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005034972,0.00001106349,0.8665456,0.1258314,0.0002903508,0.0001513661,4.603669e-7,0.00008713266,0.006579227],"genre_scores_gemma":[0.7283336,0.00000197326,0.1688332,0.09953798,0.0006400673,0.0000700278,0.000001866778,0.00001415367,0.00256711],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9406073,"threshold_uncertainty_score":0.3583947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03108233490367638,"score_gpt":0.2676836904445121,"score_spread":0.2366013555408357,"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."}}