{"id":"W3206996280","doi":"10.18653/v1/2022.findings-naacl.184","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: NAACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Question answering; Computer science; Open domain; Task (project management); Language model; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Scale (ratio); Training set; Information retrieval; Resource (disambiguation); Natural language; Natural language understanding","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":[0.003240149,0.0027537,0.001339618,0.004291655,0.001685424,0.001902224,0.004162477,0.003541775,0.007030259],"category_scores_gemma":[0.01456703,0.0007344283,0.002131494,0.003417784,0.0009826336,0.003668457,0.003821325,0.00369116,0.01009624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001911846,"about_ca_system_score_gemma":0.003238328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02128139,"about_ca_topic_score_gemma":0.04003023,"domain_scores_codex":[0.9962774,0.001265941,0.0003632263,0.001118824,0.0007297485,0.0002449679],"domain_scores_gemma":[0.9919264,0.003065468,0.0003714046,0.002040377,0.00192168,0.0006747278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006707046,0.001996464,0.01124678,0.002733633,0.0003327942,0.0005369476,0.001044716,0.0125628,0.01286849,0.00503112,0.8091158,0.1418597],"study_design_scores_gemma":[0.001248856,0.001000786,0.03474633,0.000456436,0.0003481478,0.001633024,0.001498108,0.2805348,0.03006458,0.02164355,0.6264046,0.0004207354],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1254331,0.004465863,0.1200477,0.003374419,0.00120153,0.002841135,0.6442641,0.08274676,0.0156254],"genre_scores_gemma":[0.0571815,0.0003448961,0.0730136,0.0008548268,0.0001692472,0.00179946,0.8618942,0.001079858,0.003662417],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02128139,"threshold_uncertainty_score":0.04231507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02494648340920045,"score_gpt":0.2847366473702726,"score_spread":0.2597901639610721,"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."}}