{"id":"W81387029","doi":"","title":"Learning to Classify Questions","year":2005,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Software portability; Computer science; Question answering; Artificial intelligence; Natural language processing; Boosting (machine learning); Machine learning; Set (abstract data type); Support vector machine; Feature (linguistics); Natural language; Training set; Questions and answers; Replicate; Linguistics; Programming language","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":[0.00008872826,0.00003511828,0.00003518494,0.00004104714,0.00006107504,0.00006165733,0.0002690651,0.00001696847,0.00004649755],"category_scores_gemma":[0.00003089312,0.00003184423,0.00001410434,0.000111102,0.000002926162,0.0001834751,0.0001155286,0.0000733997,0.0006389706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002336213,"about_ca_system_score_gemma":0.0000169187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000201892,"about_ca_topic_score_gemma":0.00002695157,"domain_scores_codex":[0.9995695,0.00001464975,0.00007013181,0.0001475111,0.00008299206,0.0001152682],"domain_scores_gemma":[0.9996884,0.00001794606,0.000008432203,0.0002004144,0.00002032061,0.00006452655],"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":[2.402697e-7,0.0000127524,0.000488362,8.542959e-7,0.000001858082,0.000001240451,0.0008894742,0.05401404,0.0006329441,0.3816335,0.001782583,0.5605422],"study_design_scores_gemma":[0.00004581293,0.00002091254,0.0008417437,0.000004579362,5.187133e-7,0.00000398511,0.00002276466,0.7976066,0.0004088691,0.0007143657,0.2002511,0.00007879565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01204738,0.000008479659,0.9400183,0.01128811,0.0000736884,0.00002949454,1.895794e-8,0.0002730731,0.03626147],"genre_scores_gemma":[0.5964978,6.618175e-7,0.3952964,0.0008772868,0.0000715663,0.000002745269,4.925926e-8,0.000001541143,0.007251956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7435925,"threshold_uncertainty_score":0.8212888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02582030916985392,"score_gpt":0.2766250302420155,"score_spread":0.2508047210721616,"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."}}