{"id":"W2492447297","doi":"10.4018/978-1-60566-766-9.ch014","title":"Machine Learning in Natural Language Processing","year":2010,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Agricultural Research Institute of Ontario","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Information extraction; Software deployment; Text processing; Natural (archaeology); Software engineering","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0002498778,0.0005224502,0.0004806076,0.0002097951,0.0001403025,0.0004365375,0.001651054,0.0006235239,0.0000111573],"category_scores_gemma":[0.0000790015,0.0004753716,0.0001389333,0.0000729063,0.0001007456,0.0002688366,0.0007293284,0.002415925,0.00004132059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002381889,"about_ca_system_score_gemma":0.0002605725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000169156,"about_ca_topic_score_gemma":0.0003879484,"domain_scores_codex":[0.9977894,0.00002750718,0.0004084324,0.0007810554,0.0005103078,0.0004832824],"domain_scores_gemma":[0.998799,0.000032078,0.0003355078,0.0005960298,0.0001253958,0.0001120324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001045683,0.000006971713,0.00002198702,0.00008726559,0.00001053101,0.0005400061,0.0005445422,5.752194e-7,0.0007002144,0.6750406,0.00004016699,0.3229967],"study_design_scores_gemma":[0.0007181867,0.0001312859,0.00002097241,0.001685981,0.00003834704,0.0006276891,0.00001972403,0.008728513,0.003821028,0.9601979,0.02190882,0.002101604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.00009842357,0.04167841,0.01253743,0.0002021191,0.0005709645,0.0004233918,0.0000142968,0.002561506,0.9419135],"genre_scores_gemma":[0.6362053,0.000007711853,0.2644411,0.0008217152,0.0003348971,0.00002015512,0.00001323183,0.00009162457,0.0980643],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8438492,"threshold_uncertainty_score":0.9998856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008130415791064697,"score_gpt":0.2564115843428126,"score_spread":0.2482811685517479,"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."}}