{"id":"W4281263937","doi":"10.18653/v1/2022.findings-acl.117","title":"Two-Step Question Retrieval for Open-Domain QA","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Search engine indexing; Inference; Computer science; Information retrieval; Labrador Retriever; Pipeline (software); Squid; Domain (mathematical analysis); Artificial intelligence; Open domain; Question answering; Mathematics; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002752127,0.0001305627,0.0002299901,0.00009888577,0.000883749,0.000173205,0.001828489,0.00005003557,0.00001596486],"category_scores_gemma":[0.005575283,0.0001368753,0.0001903522,0.000408287,0.00001663498,0.0001012269,0.001151931,0.0001999711,0.000002792136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008473317,"about_ca_system_score_gemma":0.0002969741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000289652,"about_ca_topic_score_gemma":0.000004086164,"domain_scores_codex":[0.9978446,0.0001602797,0.0005187328,0.0003884351,0.0008249358,0.0002630402],"domain_scores_gemma":[0.9965611,0.001392719,0.0007741456,0.0002953341,0.0009346213,0.00004211784],"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":[0.00005325165,0.00007026852,0.002161713,0.00002135828,0.00005524075,2.138416e-7,0.0002464675,0.1313298,0.00005418372,0.858124,0.007711489,0.0001719876],"study_design_scores_gemma":[0.001643053,0.0001404066,0.001540166,0.00001641028,0.00003195504,0.000001874479,0.00005904793,0.5443206,0.0001660603,0.3976342,0.05424628,0.0001999634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008560319,0.00006265241,0.9779735,0.00294859,0.005866357,0.001836336,0.0008311225,0.00009973332,0.001821392],"genre_scores_gemma":[0.6672058,7.500026e-7,0.3286735,0.0005642948,0.0005328861,0.0001483552,0.0002442392,0.00002752873,0.002602587],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6586455,"threshold_uncertainty_score":0.6797172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01875750815666395,"score_gpt":0.2925474942045004,"score_spread":0.2737899860478364,"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."}}