{"id":"W3198536471","doi":"10.1145/3446426","title":"Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Ministry of Science and Technology, Taiwan","keywords":"Computer science; Information retrieval; Leverage (statistics); Query expansion; Term (time); Artificial intelligence; Query language; Rewriting; Context (archaeology); Natural language processing; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000496423,0.0001454187,0.0001656894,0.0002161749,0.0003357707,0.0005185945,0.0003052938,0.00008649816,0.000004772251],"category_scores_gemma":[0.0001052625,0.000154664,0.00003461016,0.0004245663,0.00002209602,0.004239299,0.00001968559,0.0001713358,0.00001055916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145542,"about_ca_system_score_gemma":0.00007322223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005550932,"about_ca_topic_score_gemma":0.000004671011,"domain_scores_codex":[0.9984218,0.0001005689,0.0006097925,0.0002842551,0.000391386,0.0001921899],"domain_scores_gemma":[0.9986579,0.00009397072,0.0001992423,0.0006794725,0.0002414908,0.0001279673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003054335,0.0001207247,0.00111266,0.000508378,0.00004550224,0.000006653342,0.02133304,0.8744144,0.001812551,0.01589885,0.00002925411,0.08468747],"study_design_scores_gemma":[0.0004142899,0.00002306307,0.001492969,0.00005457389,0.000005677213,0.00006087293,0.002018023,0.9951903,0.0003280869,0.00003348016,0.0002060565,0.0001725693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03589182,0.0000229501,0.9622856,0.0004043916,0.0004297492,0.0003142125,0.00001923943,0.0002095034,0.0004224817],"genre_scores_gemma":[0.824791,0.00000398228,0.1746682,0.0003411911,0.00003373329,0.00002986314,0.00004975566,0.000006710455,0.00007564544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7888991,"threshold_uncertainty_score":0.6307016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05929551466071249,"score_gpt":0.2863921894774662,"score_spread":0.2270966748167537,"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."}}