{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001742403,0.00132807,0.0004812029,0.00234657,0.0006093014,0.001066372,0.001153072,0.001200998,0.005410635],"category_scores_gemma":[0.005075821,0.0004741595,0.001106131,0.001176559,0.0003786236,0.004352855,0.001425427,0.001764004,0.003402153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000748759,"about_ca_system_score_gemma":0.001149483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003585689,"about_ca_topic_score_gemma":0.007076901,"domain_scores_codex":[0.9989492,0.0003059867,0.00008963064,0.0003342993,0.0002576342,0.00006324433],"domain_scores_gemma":[0.9966295,0.00190596,0.0003468571,0.0004638332,0.0004917067,0.0001621629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001382419,0.0003432345,0.01660657,0.00216992,0.0005245383,0.001516815,0.001816909,0.06337288,0.05673615,0.03425708,0.2092075,0.6120659],"study_design_scores_gemma":[0.00008221811,0.0003891589,0.007363233,0.0001501972,0.0001578071,0.00208666,0.0004630442,0.8319927,0.02741626,0.03356926,0.09615946,0.0001700463],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04981547,0.001405821,0.8725043,0.001310612,0.0007774898,0.000495,0.01842877,0.04917219,0.006090372],"genre_scores_gemma":[0.3935353,0.0008348588,0.5617974,0.0005349647,0.0003985744,0.0004769096,0.03417835,0.001630881,0.006612766],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005410635,"threshold_uncertainty_score":0.01810038,"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."}}