{"id":"W2094723464","doi":"10.1109/nlpke.2007.4368014","title":"Recognizing Biomedical Named Entities in the Absence of Human Annotated Corpora","year":2007,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Annotation; Artificial intelligence; Classifier (UML); Task (project management); Named-entity recognition; Natural language processing; Training set; Support vector machine; Domain (mathematical analysis); Process (computing); Supervised learning; Labeled data; Machine learning; Information retrieval","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":[0.0100742,0.001241576,0.001787688,0.004106713,0.001239126,0.002393742,0.002396172,0.002863883,0.001563019],"category_scores_gemma":[0.03518516,0.0007488903,0.0008610955,0.003519516,0.001417895,0.006919385,0.002612598,0.001852123,0.002291101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007551591,"about_ca_system_score_gemma":0.001461432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001493646,"about_ca_topic_score_gemma":0.003765582,"domain_scores_codex":[0.9920642,0.0039261,0.0006827052,0.001997085,0.001114899,0.0002150636],"domain_scores_gemma":[0.950731,0.0364552,0.003174015,0.006297452,0.002842939,0.0004993912],"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":[0.001278762,0.0007320777,0.02317154,0.00271693,0.0003760608,0.003196485,0.002530284,0.04802118,0.0837971,0.01683934,0.05188429,0.7654559],"study_design_scores_gemma":[0.0001605031,0.0004026663,0.01894539,0.000436051,0.000335181,0.003507146,0.002180866,0.6956273,0.1099175,0.0575114,0.1107861,0.000189836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1350536,0.003742783,0.8363429,0.002684401,0.0004544739,0.0003540236,0.007221217,0.007253833,0.006892732],"genre_scores_gemma":[0.327217,0.001512297,0.6300633,0.000643681,0.000488594,0.0006322581,0.03485103,0.0005501114,0.004041754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0100742,"threshold_uncertainty_score":0.05327809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04676660999294786,"score_gpt":0.2905173275352811,"score_spread":0.2437507175423332,"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."}}