{"id":"W3214455632","doi":"10.18653/v1/2021.emnlp-main.77","title":"Contextualized Query Embeddings for Conversational Search","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Leverage (statistics); Inference; Security token; Relevance (law); Pipeline (software); Information retrieval; Query expansion; Query language; Artificial intelligence","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":[0.0009613278,0.0008798506,0.0007908522,0.0009664522,0.0004169227,0.00109613,0.001613103,0.001319279,0.004236063],"category_scores_gemma":[0.006962941,0.0004818079,0.0008611562,0.001128411,0.0006807409,0.004279525,0.001462866,0.001848169,0.001862314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001176532,"about_ca_system_score_gemma":0.001007725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008016057,"about_ca_topic_score_gemma":0.01051199,"domain_scores_codex":[0.9992386,0.0002661147,0.00005120913,0.0002358174,0.0001262876,0.00008193574],"domain_scores_gemma":[0.9986927,0.0006620416,0.0001084261,0.0002835164,0.0001979134,0.00005539605],"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":[0.0006578758,0.0004651977,0.003538317,0.0005986327,0.0001858383,0.0003147981,0.00107127,0.438065,0.01801806,0.1217575,0.02413343,0.391194],"study_design_scores_gemma":[0.00001444508,0.00005380439,0.000244796,0.00001363975,0.00002099567,0.00006621602,0.00004721359,0.9640874,0.001342468,0.0311892,0.002904789,0.00001513669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02703959,0.001297144,0.9645652,0.0005952728,0.00007895151,0.0001178203,0.001227289,0.002586653,0.002492253],"genre_scores_gemma":[0.7218541,0.0009861687,0.2639742,0.0004650004,0.0001956876,0.0004344167,0.004041268,0.0004286384,0.007620572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008016057,"threshold_uncertainty_score":0.01593876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.092333595524727,"score_gpt":0.4395395092037929,"score_spread":0.3472059136790658,"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."}}