{"id":"W2963301888","doi":"10.18653/v1/n18-4017","title":"Training a Ranking Function for Open-Domain Question Answering","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Advanced Research Projects Agency; Tencent; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Computer science; Question answering; Artificial intelligence; Natural language processing; Paragraph; Reading (process); Reading comprehension; Relevance (law); Ranking (information retrieval); Similarity (geometry); Task (project management); Domain (mathematical analysis); Information retrieval; Linguistics; World Wide Web","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002836384,0.001298174,0.001435322,0.001495161,0.0005359093,0.0008921844,0.001831448,0.002537062,0.005861344],"category_scores_gemma":[0.00956447,0.000434116,0.0007927601,0.001025679,0.00048049,0.001960793,0.0009567281,0.001819315,0.002991301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009439907,"about_ca_system_score_gemma":0.001003639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003819284,"about_ca_topic_score_gemma":0.005213969,"domain_scores_codex":[0.9985757,0.0006301322,0.00009146707,0.0003229447,0.0002194794,0.0001602958],"domain_scores_gemma":[0.9959481,0.002772916,0.000163446,0.0002948553,0.0006858507,0.0001347934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004428832,0.0006287369,0.003097308,0.0003427968,0.0001126571,0.0001503233,0.000180755,0.1847718,0.007288966,0.007346729,0.01884642,0.7767906],"study_design_scores_gemma":[0.0000260061,0.00009342275,0.0003923796,0.00001098765,0.00001316963,0.00003193699,0.00002407576,0.992925,0.001373721,0.004161911,0.0009385263,0.000008899889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08384327,0.002302435,0.9015188,0.0008249719,0.0001871608,0.0002118582,0.0005394733,0.006632032,0.003939972],"genre_scores_gemma":[0.6745124,0.000576982,0.3119742,0.0005616315,0.0003771847,0.0004239853,0.003340441,0.0004334611,0.007799556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005861344,"threshold_uncertainty_score":0.01960814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07747956067232864,"score_gpt":0.3136400354574098,"score_spread":0.2361604747850811,"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."}}