{"id":"W4385732413","doi":"10.1109/tkde.2023.3303916","title":"XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Computer science; Question answering; Robustness (evolution); Construct (python library); Semantics (computer science); Simple (philosophy); Artificial intelligence; Machine learning; Information retrieval; Natural language processing; 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":[0.0005756271,0.0001885532,0.0001869442,0.0003080271,0.0002994668,0.0001885534,0.0005565764,0.00007441099,0.000003004374],"category_scores_gemma":[0.00002815739,0.0002121597,0.00003120855,0.0004008668,0.00002506193,0.0008872452,0.0000301548,0.0001917793,0.00001325737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009733029,"about_ca_system_score_gemma":0.00003835267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002154811,"about_ca_topic_score_gemma":0.00004390654,"domain_scores_codex":[0.9986609,0.00002751584,0.000275406,0.0005880281,0.0001217472,0.0003263613],"domain_scores_gemma":[0.9986726,0.0003463136,0.00004170182,0.0007981511,0.00003382349,0.0001073891],"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":[0.00001587942,0.00005656665,0.00001176891,0.00040226,0.00009192302,0.000009898971,0.0006429272,0.8938682,0.003194016,0.03828159,0.001288058,0.0621369],"study_design_scores_gemma":[0.0003746499,0.00002612377,0.00001294563,0.0001427373,0.00002166211,0.00002101056,0.0001105994,0.9969558,0.000531226,0.000264644,0.001307565,0.0002310082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007091529,0.00006031447,0.9963384,0.0001280938,0.001009642,0.0002267091,0.0009351571,0.0005468038,0.00004568847],"genre_scores_gemma":[0.8298508,0.00007972344,0.1690049,0.00002351769,0.0001486477,0.00004800264,0.0007787073,0.0000336331,0.00003209638],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8291416,"threshold_uncertainty_score":0.8651623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1505179283078189,"score_gpt":0.3267831472600723,"score_spread":0.1762652189522534,"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."}}