{"id":"W3007129127","doi":"10.18653/v1/2020.emnlp-main.713","title":"Unsupervised Question Decomposition for Question Answering","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Samsung Advanced Institute of Technology; Samsung; Open Philanthropy Project; Nvidia; National Science Foundation","keywords":"Question answering; Computer science; Leverage (statistics); Open domain; Artificial intelligence; Heuristic; Baseline (sea); Information retrieval; Machine learning; Natural language processing","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":[0.000340221,0.0002121596,0.0002292268,0.0000967887,0.00008584566,0.0003019949,0.0007316377,0.0002187675,0.000006270684],"category_scores_gemma":[0.00005188347,0.0002269921,0.0001248182,0.00008548341,0.000008934819,0.0002938517,0.0006778508,0.0002708042,0.00001690597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133636,"about_ca_system_score_gemma":0.0001022222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000139454,"about_ca_topic_score_gemma":0.00001649638,"domain_scores_codex":[0.9984051,0.00008011765,0.0003320359,0.0007685371,0.0002078524,0.0002063406],"domain_scores_gemma":[0.9989974,0.00005823801,0.0001136426,0.000591294,0.0001398585,0.00009960591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003697207,0.00008947319,0.0002451472,0.0009808964,0.00007145081,0.00001121827,0.001284846,0.08957665,0.01281944,0.6924926,0.0007723676,0.2016189],"study_design_scores_gemma":[0.0001796362,0.0000394116,0.0002443543,0.0001607198,0.00001212931,0.000003114995,0.000005231734,0.9214764,0.00273952,0.07449722,0.000395279,0.0002469821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005821367,0.00008088332,0.9856784,0.005042036,0.001251478,0.0006300119,0.000004768508,0.0008343815,0.0006566262],"genre_scores_gemma":[0.4095308,0.0000169379,0.589533,0.0003701143,0.0003067609,0.0001107238,0.00006382634,0.00001428855,0.00005348475],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8318998,"threshold_uncertainty_score":0.9256469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04192274640212695,"score_gpt":0.3217740653162895,"score_spread":0.2798513189141626,"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."}}