{"id":"W2283763484","doi":"10.1145/2651444","title":"Recognition of Patient-Related Named Entities in Noisy Tele-Health Texts","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Relationship extraction; Noise (video); Information extraction; Information retrieval; Sentence; Named-entity recognition; Phone; Filter (signal processing); Machine learning; Task (project management); Speech recognition","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":[0.0002388866,0.0001089895,0.0002395428,0.0007053892,0.00005159025,0.00002120632,0.0003245322,0.000170071,0.000005067765],"category_scores_gemma":[0.00004294555,0.0001046585,0.00002733228,0.00054758,0.00006530841,0.0001404209,0.00001960984,0.0002216065,0.00001746163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009010051,"about_ca_system_score_gemma":0.00007245054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005945543,"about_ca_topic_score_gemma":0.0001190809,"domain_scores_codex":[0.9987791,0.00006453398,0.0005193871,0.0002849713,0.0001525695,0.0001994078],"domain_scores_gemma":[0.9991356,0.0000515398,0.0001504899,0.000495145,0.0001065993,0.00006068104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001258619,0.0002482374,0.000653104,0.0001089565,0.00004568328,0.000007870513,0.003188001,0.002225367,0.0001130021,0.01843692,0.00003410886,0.9749262],"study_design_scores_gemma":[0.007012792,0.00994058,0.0004141469,0.005342904,0.00009814198,0.001383459,0.05030588,0.3169061,0.1017286,0.4795405,0.02443557,0.002891244],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2769403,0.001394723,0.7183518,0.001657358,0.0008687162,0.0004228275,0.000007018521,0.0002102558,0.0001470003],"genre_scores_gemma":[0.9948007,0.0001986214,0.004830293,0.0000238995,0.000004745547,0.00005631526,0.000001775863,0.00000678393,0.00007688715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9720349,"threshold_uncertainty_score":0.426785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03429504103428756,"score_gpt":0.2580997059002944,"score_spread":0.2238046648660069,"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."}}