{"id":"W2557764419","doi":"10.18653/v1/w17-2623","title":"NewsQA: A Machine Comprehension Dataset","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":742,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Textual entailment; Computer science; Comprehension; Natural language processing; Artificial intelligence; Matching (statistics); Set (abstract data type); Word (group theory); Process (computing); Exploratory analysis; Information retrieval; Machine learning; Logical consequence; Data science; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001344247,0.001652982,0.0006319559,0.003437625,0.0008120087,0.001091593,0.001919042,0.002348515,0.01284014],"category_scores_gemma":[0.008463047,0.0002734374,0.0008662831,0.002464755,0.0004041905,0.001697431,0.001117218,0.00147741,0.01026854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001092425,"about_ca_system_score_gemma":0.001147083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008136968,"about_ca_topic_score_gemma":0.01808344,"domain_scores_codex":[0.9985902,0.0004121923,0.0001829454,0.0003540167,0.0003623795,0.00009827971],"domain_scores_gemma":[0.9955834,0.001979935,0.0003145472,0.0006147433,0.00120407,0.0003034726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003956275,0.0007825175,0.008898137,0.00153974,0.0001448285,0.0004278564,0.0006551954,0.00272624,0.005304055,0.001945508,0.9295832,0.04759708],"study_design_scores_gemma":[0.0008791256,0.0006414271,0.04242887,0.0003069358,0.0001802876,0.0009968383,0.001350488,0.03284175,0.01283882,0.007178825,0.9001929,0.0001636532],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05718521,0.001757914,0.006196069,0.001651546,0.0002454357,0.0006567295,0.9136712,0.006984905,0.01165111],"genre_scores_gemma":[0.03252353,0.0002303554,0.008884204,0.00042317,0.0001024901,0.0006223237,0.9535761,0.0002135454,0.003424373],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01284014,"threshold_uncertainty_score":0.0429545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05848331174708454,"score_gpt":0.3064087311719761,"score_spread":0.2479254194248916,"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."}}