{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007121162,0.00006645243,0.00008282059,0.00005068119,0.0001914351,0.0002682195,0.0005084825,0.00003323484,0.00001744596],"category_scores_gemma":[0.00003228175,0.00006290535,0.00002510117,0.0001179065,0.00001355313,0.0007366026,0.0001762356,0.0000388596,0.00001202993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002976573,"about_ca_system_score_gemma":0.00003658649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004453001,"about_ca_topic_score_gemma":0.00005597227,"domain_scores_codex":[0.999256,0.00002498703,0.0001414271,0.0002916081,0.00009503245,0.0001909394],"domain_scores_gemma":[0.9995605,0.00004018734,0.00003987072,0.0002599104,0.00006342223,0.00003607872],"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":[0.0000154439,0.000008751416,0.00006125592,0.000006743966,0.000007430691,5.126536e-7,0.00236409,0.000132678,0.003800208,0.5552396,0.0001231053,0.4382402],"study_design_scores_gemma":[0.0007719361,0.0002251727,0.0003062021,0.00005589887,0.000004604122,0.00001025939,0.0002456899,0.8662101,0.001740017,0.1141346,0.01609061,0.0002048565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01188902,0.00001089796,0.9769564,0.0004142842,0.0006741917,0.0002374692,1.524791e-7,0.0001740291,0.009643527],"genre_scores_gemma":[0.5696326,2.196687e-7,0.4295827,0.0003205441,0.0002090816,0.00002173612,4.859371e-7,0.000004247133,0.0002283744],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8660774,"threshold_uncertainty_score":0.2586447,"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."}}