{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001631502,0.00009631652,0.0001386679,0.00005134024,0.00003744825,0.00005601294,0.0004301556,0.00005850364,0.00003262015],"category_scores_gemma":[0.00001533717,0.00008186326,0.00005490329,0.00008290561,0.0000111768,0.00036509,0.00007897819,0.00006571346,0.00002263879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005163775,"about_ca_system_score_gemma":0.00008000222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003243286,"about_ca_topic_score_gemma":0.000005862587,"domain_scores_codex":[0.9990788,0.00001548575,0.0002148831,0.0003529867,0.0001477128,0.0001901682],"domain_scores_gemma":[0.9991772,0.00004649712,0.0001218733,0.0004947069,0.000112204,0.00004751182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000121449,0.00004400166,0.00309757,0.00005211957,0.00003042631,5.301347e-7,0.006831217,0.00003088596,0.1089927,0.8663679,0.0002339849,0.01430659],"study_design_scores_gemma":[0.001042211,0.0001987246,0.0123648,0.00002708862,0.00000760929,0.000004452155,0.0004152364,0.9516432,0.02062809,0.009817339,0.003527424,0.0003238462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4391284,0.000005539352,0.5546282,0.001903363,0.0006299279,0.0004237734,0.000004120163,0.00009906437,0.003177586],"genre_scores_gemma":[0.9336427,7.847868e-7,0.06188478,0.00022584,0.00006734941,0.00003112583,0.000003725474,0.000007368434,0.004136275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9516123,"threshold_uncertainty_score":0.3338287,"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."}}