{"id":"W4385569686","doi":"10.18653/v1/2023.acl-long.274","title":"ConvGQR: Generative Query Reformulation for Conversational Search","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"China Scholarship Council; Tsinghua University","keywords":"Computer science; Query expansion; Conversation; Query language; Rewriting; Web search query; Information retrieval; Web query classification; Query optimization; RDF query language; Sargable; Generative grammar; Task (project management); Artificial intelligence; Search engine; Programming language; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001842114,0.002172576,0.001888786,0.001376925,0.0005726808,0.001131479,0.003069192,0.002058184,0.005994147],"category_scores_gemma":[0.005778874,0.0007359108,0.00226549,0.001239092,0.001033457,0.002957377,0.002406072,0.002476948,0.003822156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001408886,"about_ca_system_score_gemma":0.001500612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01211236,"about_ca_topic_score_gemma":0.0149379,"domain_scores_codex":[0.9983398,0.0006194072,0.00009738562,0.0004911748,0.0003089462,0.0001433459],"domain_scores_gemma":[0.9984115,0.0008740931,0.00008001952,0.0003458609,0.0002201546,0.00006829891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007259194,0.0003853741,0.001573398,0.001344929,0.0002613367,0.0006729051,0.00134562,0.1759094,0.03783297,0.01903019,0.06435166,0.6965662],"study_design_scores_gemma":[0.00007263587,0.0001532411,0.0002400984,0.00002725477,0.00005906319,0.0002586075,0.0001317592,0.9647998,0.008307786,0.01739958,0.008506636,0.00004362995],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01681295,0.002385349,0.9548326,0.0005349529,0.0001129034,0.0003374532,0.001588049,0.02058816,0.002807576],"genre_scores_gemma":[0.3698982,0.001390304,0.6047714,0.001546699,0.0002487942,0.0007224755,0.009877419,0.002481923,0.00906275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01211236,"threshold_uncertainty_score":0.02408367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08974196501350201,"score_gpt":0.3223583861389037,"score_spread":0.2326164211254017,"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."}}