{"id":"W2252096820","doi":"10.3115/v1/w14-3420","title":"Using statistical parsing to detect agrammatic aphasia","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Aphasia; Computer science; Parsing; Natural language processing; Artificial intelligence; Classifier (UML); Context (archaeology); Grammar; Top-down parsing; Agrammatism; Speech recognition; Linguistics; Psychology; Cognitive psychology; Sentence","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":[0.0003114334,0.0001017558,0.0001248972,0.0000999036,0.0001119485,0.0002440273,0.0005588413,0.00003995514,0.00001370798],"category_scores_gemma":[0.0002599507,0.00008192484,0.00002096128,0.000303327,0.00002123001,0.000239935,0.0001994314,0.00009501058,0.00003618204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004204415,"about_ca_system_score_gemma":0.00001978327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000418271,"about_ca_topic_score_gemma":0.000009123613,"domain_scores_codex":[0.9990475,0.00006187799,0.0001566371,0.0002658785,0.0002074086,0.0002606907],"domain_scores_gemma":[0.9993203,0.0001260848,0.00003442915,0.0003524561,0.0000470655,0.000119632],"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":[0.000003067229,0.00001220322,0.0000433464,0.0000357766,0.000004778021,0.00002481789,0.0002222032,0.00002870809,0.01618017,0.2721254,0.0003752659,0.7109442],"study_design_scores_gemma":[0.000156492,0.0001531437,0.00008917407,0.0001032644,0.00001009212,0.0001558778,0.000009943955,0.5212179,0.07957475,0.3968936,0.001179641,0.000456159],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002046397,0.0000508741,0.9960298,0.0002145183,0.00007983099,0.0000977667,2.740803e-7,0.0006815054,0.0007990588],"genre_scores_gemma":[0.4065107,9.618616e-8,0.5930803,0.0003620588,0.0000219362,0.000002029928,2.104735e-7,0.000004821971,0.00001779196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7104881,"threshold_uncertainty_score":0.3340798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0253972100265108,"score_gpt":0.3184345147845668,"score_spread":0.293037304758056,"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."}}