{"id":"W2970161670","doi":"10.18653/v1/w19-5025","title":"Can Character Embeddings Improve Cause-of-Death Classification for Verbal Autopsy Narratives?","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Verbal autopsy; Character (mathematics); Narrative; Coding (social sciences); Computer science; Natural language processing; Autopsy; Artificial intelligence; Word (group theory); Cause of death; Speech recognition; Linguistics; Medicine; Pathology; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003017927,0.001671258,0.0007110152,0.001788091,0.0004942154,0.001912508,0.00106035,0.001384536,0.002255857],"category_scores_gemma":[0.01592763,0.0003362308,0.0009088417,0.001298331,0.0005177694,0.004604941,0.00138532,0.002087265,0.002255236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007331839,"about_ca_system_score_gemma":0.0006401083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003361642,"about_ca_topic_score_gemma":0.005485199,"domain_scores_codex":[0.9989204,0.0004861294,0.0000783607,0.0002941573,0.0001016162,0.0001193842],"domain_scores_gemma":[0.993654,0.003983793,0.0005707165,0.0007389276,0.0008400662,0.0002125043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001261475,0.0008479537,0.07496865,0.0005612711,0.0005720694,0.0003035237,0.00123614,0.05924307,0.01277931,0.00559261,0.0225557,0.8200783],"study_design_scores_gemma":[0.00004426776,0.0002500529,0.01112411,0.0001815482,0.0001845801,0.0002229421,0.0005326878,0.952317,0.008331261,0.01954763,0.007190388,0.00007349031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5642365,0.00520352,0.3992959,0.008495227,0.001616671,0.0003465787,0.005493816,0.005344147,0.009967589],"genre_scores_gemma":[0.9210026,0.0007262569,0.06916663,0.0004468075,0.0003296186,0.0001236698,0.004827933,0.0001766224,0.003199775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003361642,"threshold_uncertainty_score":0.01596051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03445423808597654,"score_gpt":0.282879640644713,"score_spread":0.2484254025587365,"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."}}