{"id":"W1484050045","doi":"10.1007/11424918_34","title":"A Supervised Learning Approach to Acronym Identification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":94,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Acronym; Computer science; Identification (biology); Task (project management); Supervised learning; Artificial intelligence; Space (punctuation); Machine learning; Artificial neural network","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":[0.000452559,0.0002353199,0.0002114727,0.0001861873,0.0001246898,0.0001004323,0.0007532405,0.0003747795,0.000009469071],"category_scores_gemma":[0.0001782714,0.0002112503,0.00006968353,0.0001439407,0.0003963857,0.000004124705,0.0004085779,0.0003562642,0.00002886286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004913131,"about_ca_system_score_gemma":0.0001433341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004882359,"about_ca_topic_score_gemma":0.00001552079,"domain_scores_codex":[0.9982122,0.00002085538,0.0002468568,0.0008754884,0.0003161771,0.0003284773],"domain_scores_gemma":[0.9992217,0.00003083149,0.00008367715,0.0004653352,0.00008818092,0.0001102974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001269887,0.00002282404,0.00004243696,0.00001883917,0.00000921336,0.000002408874,0.000269306,0.01303162,0.02332393,0.0001062452,0.00009454097,0.9630659],"study_design_scores_gemma":[0.002089694,0.002459971,0.002629528,0.000831464,0.00008618,0.0002812558,0.00001189751,0.2122613,0.1556086,0.01053474,0.6084343,0.004771095],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002691279,0.0005804797,0.9924932,0.0003228431,0.0003160285,0.0001770685,0.000003338145,0.00003642986,0.003379353],"genre_scores_gemma":[0.6469451,0.0001177395,0.344156,0.001725261,0.001638291,0.00002441949,0.0001179988,0.00005399669,0.005221254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9582949,"threshold_uncertainty_score":0.8614538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01965548986135455,"score_gpt":0.2625764853685928,"score_spread":0.2429209955072383,"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."}}