{"id":"W4285155190","doi":"10.18653/v1/2022.findings-acl.168","title":"Question Generation for Reading Comprehension Assessment by Modeling How and What to Ask","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading comprehension; Computer science; Comprehension; Reading (process); Focus (optics); Artificial intelligence; Natural language processing; Mathematics education; Linguistics; Psychology","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":[0.001384052,0.0001257703,0.0001887454,0.00012767,0.000818965,0.0003772611,0.000422081,0.00004999765,0.000001937986],"category_scores_gemma":[0.001474755,0.0001335866,0.00009540474,0.0002184587,0.000007190079,0.0002366003,0.0004047871,0.0001445504,3.193307e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006711242,"about_ca_system_score_gemma":0.0001043806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001354534,"about_ca_topic_score_gemma":0.000001859759,"domain_scores_codex":[0.9982722,0.0001126565,0.0003454052,0.0003918821,0.0006732062,0.000204696],"domain_scores_gemma":[0.9980315,0.0005873343,0.0003788542,0.0001833085,0.0007699325,0.00004905396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001040521,0.00003879185,0.0007179411,0.00002574517,0.00003620726,6.431815e-8,0.0003929105,0.8053724,0.001398206,0.1857685,0.005039982,0.001198895],"study_design_scores_gemma":[0.0004164988,0.00009218402,0.0002115813,0.00002271014,0.00002319028,8.036712e-7,0.0001022306,0.971087,0.0001977648,0.02127923,0.00642707,0.0001396788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03809086,0.00007331541,0.9552134,0.003431471,0.002190955,0.0007782344,0.0001493393,0.00004544485,0.00002694521],"genre_scores_gemma":[0.8495212,0.000005473347,0.1490762,0.000419425,0.000255849,0.0001382724,0.0002700254,0.00001579678,0.0002977907],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8114303,"threshold_uncertainty_score":0.62989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02239636680911099,"score_gpt":0.2829373594837503,"score_spread":0.2605409926746393,"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."}}