{"id":"W2213189003","doi":"","title":"Chemistry-specific Features and Heuristics for Developing a CRF-based Chemical Named Entity Recogniser","year":2013,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"Wellcome Trust","keywords":"Conditional random field; Named-entity recognition; Heuristics; Computer science; Artificial intelligence; Task (project management); Natural language processing; Training set; Set (abstract data type); Sequence labeling; Security token; Search engine indexing; Pattern recognition (psychology); Machine learning","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":[0.0003012395,0.0001047675,0.0001409386,0.0000332426,0.0001894998,0.00002830966,0.0003561892,0.000179438,0.00003782733],"category_scores_gemma":[0.0002948204,0.00008880873,0.000068501,0.00009037227,0.0008045308,0.000005607744,0.0002479913,0.0001837012,0.000009298843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000289054,"about_ca_system_score_gemma":0.00008904638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006495626,"about_ca_topic_score_gemma":0.000001151913,"domain_scores_codex":[0.9990126,0.00007370791,0.00009865487,0.0003038403,0.0002092833,0.0003019384],"domain_scores_gemma":[0.9991474,0.0001722759,0.00004603135,0.0002715715,0.0002711584,0.00009156037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006184896,0.0001731127,0.00170505,0.0006106044,0.0001601786,0.000009527594,0.003181349,0.000002961379,0.8267028,0.0000864945,0.1042115,0.06253795],"study_design_scores_gemma":[0.002697238,0.0003637613,0.01511243,0.0002010399,0.00003458596,0.00001628298,0.01163692,0.0002824569,0.6301826,0.001281227,0.3376874,0.0005040669],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898607,0.0005994247,0.006633611,0.002471361,0.00003125364,0.0003094266,0.00001211386,0.0000151967,0.00006690514],"genre_scores_gemma":[0.984329,0.0005420018,0.01467785,0.00007070231,0.0001060319,0.00001052411,0.00006567397,0.00001381643,0.0001844293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2334759,"threshold_uncertainty_score":0.3621515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06544131363573949,"score_gpt":0.2888142198452974,"score_spread":0.2233729062095579,"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."}}