{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004580902,0.00004369024,0.00005782075,0.0001960399,0.0000283247,0.00005583337,0.0003303813,0.00002236088,0.0000436377],"category_scores_gemma":[0.00008350173,0.0000428707,0.00001399521,0.0006964275,0.000002989644,0.000120059,0.0003447331,0.0001218777,0.001548265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004537136,"about_ca_system_score_gemma":0.00004219954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001071617,"about_ca_topic_score_gemma":0.0000390618,"domain_scores_codex":[0.9991807,0.00004129276,0.0001164007,0.0002465537,0.0002111728,0.000203912],"domain_scores_gemma":[0.9996209,0.0000766112,0.000007089864,0.0001815607,0.00002925241,0.00008461071],"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":[0.000005434236,0.00001479303,0.01999852,0.00001829265,0.000007118801,0.00005657635,0.03341191,0.8108938,0.0008090652,0.06995865,0.00189495,0.06293093],"study_design_scores_gemma":[0.0001567373,0.00005209319,0.02434217,0.00002179651,3.951648e-7,0.000002658618,0.0001981422,0.9680792,0.0002002633,0.001244615,0.005585127,0.0001167988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5554564,0.000004729687,0.4280948,0.01070999,0.0001638231,0.0002162614,1.500964e-7,0.0003005849,0.0050533],"genre_scores_gemma":[0.9574155,0.000002330758,0.03425971,0.0006038544,0.00002623181,0.00001211692,7.050983e-7,0.000003919896,0.007675657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4019591,"threshold_uncertainty_score":0.9992291,"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."}}