{"id":"W4385567884","doi":"10.1145/3580305.3599411","title":"Learning to Relate to Previous Turns in Conversational Search","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Conversation; Information retrieval; Task (project management); Query expansion; Selection (genetic algorithm); Context (archaeology); Web search query; Query language; Search engine; Artificial intelligence","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":[0.00515685,0.001755648,0.00157439,0.002455368,0.001226994,0.001596868,0.002243943,0.002043837,0.001654846],"category_scores_gemma":[0.01623455,0.0008035532,0.001377781,0.001868685,0.0009029786,0.004291927,0.002075529,0.001991978,0.001465415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044614,"about_ca_system_score_gemma":0.001534903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01239927,"about_ca_topic_score_gemma":0.01742763,"domain_scores_codex":[0.9961336,0.0018659,0.0001894202,0.001113133,0.0003496592,0.0003483387],"domain_scores_gemma":[0.9906545,0.006970423,0.0006141789,0.0006925792,0.0007533149,0.0003149443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002929551,0.001128286,0.0440986,0.001521869,0.0006185937,0.0007122211,0.005081209,0.1247183,0.03026358,0.006225096,0.01877475,0.763928],"study_design_scores_gemma":[0.0000984859,0.0003628141,0.007518449,0.00007597174,0.0002340293,0.0003895524,0.0006556131,0.9664074,0.005991135,0.01336679,0.004802917,0.00009695975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3624282,0.00983003,0.6117699,0.001474566,0.0002065704,0.0005169644,0.001246136,0.00500047,0.007527158],"genre_scores_gemma":[0.9170279,0.0009453468,0.07429878,0.0004775949,0.0002800565,0.0003149322,0.002133869,0.0002679722,0.004253427],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01239927,"threshold_uncertainty_score":0.02727234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04087385543414748,"score_gpt":0.2949330662295956,"score_spread":0.2540592107954481,"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."}}