{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001150964,0.00005610389,0.00008996335,0.0001246943,0.00004263634,0.00003291371,0.0006808881,0.00003632983,0.00002115085],"category_scores_gemma":[0.00004217157,0.0000386721,0.00002290247,0.0003975805,0.00007861767,0.0001493384,0.00009973841,0.0001032727,0.000006224838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001399967,"about_ca_system_score_gemma":0.00002490356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003074361,"about_ca_topic_score_gemma":0.0001293829,"domain_scores_codex":[0.9990472,0.00003787276,0.0002863781,0.0001648371,0.0002790692,0.0001846075],"domain_scores_gemma":[0.9994391,0.0001292169,0.00006782408,0.0002950931,0.00003900116,0.00002972769],"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":[0.00001556167,0.0005551976,0.04442674,0.0001230701,0.00003346636,0.0003771913,0.04017691,0.00008193772,0.07020112,0.6195978,0.00205695,0.222354],"study_design_scores_gemma":[0.004400883,0.001005795,0.2778846,0.0007581193,0.00001740696,0.0002457891,0.01736864,0.4397058,0.06368694,0.1858968,0.00718949,0.001839763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5793338,0.0000222363,0.4156618,0.0003155279,0.00012843,0.00006611251,2.180492e-7,0.00004161855,0.00443025],"genre_scores_gemma":[0.975552,0.00000202078,0.02404951,0.0002333877,0.00002572048,0.000001492249,0.000001033845,0.000002053712,0.0001327838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4396239,"threshold_uncertainty_score":0.1577003,"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."}}