{"id":"W4403582839","doi":"10.1145/3627673.3679534","title":"Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Search","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Beijing Jiaotong University","keywords":"Computer science; Query expansion; Relevance (law); Sargable; Information retrieval; Query optimization; Query language; Web search query; Representation (politics); Relevance feedback; Web query classification; RDF query language; Query by Example; Search engine; Natural language processing; Artificial intelligence; Image retrieval","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":[0.002546571,0.001131371,0.001240563,0.001528892,0.0005763392,0.001249085,0.001659521,0.001262874,0.001614252],"category_scores_gemma":[0.01007389,0.0004869319,0.0009608516,0.00149531,0.0006836307,0.00375325,0.001766496,0.001621537,0.001637493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009187549,"about_ca_system_score_gemma":0.001743102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01395827,"about_ca_topic_score_gemma":0.01336651,"domain_scores_codex":[0.9972626,0.001013131,0.0002032488,0.0008257155,0.0005093938,0.0001858854],"domain_scores_gemma":[0.9969015,0.001685461,0.0001823306,0.0006154961,0.0005044715,0.0001107526],"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":[0.001058109,0.0009438402,0.006799415,0.0008305497,0.000290634,0.000450192,0.001696899,0.1191991,0.06489132,0.00681524,0.01637513,0.7806495],"study_design_scores_gemma":[0.00006818787,0.0003896526,0.002232837,0.00002350593,0.0001071914,0.0004149767,0.0003291125,0.9680053,0.01564272,0.006292881,0.006407066,0.0000866216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1745391,0.003474212,0.806131,0.0007477577,0.0001391257,0.0005207356,0.001079429,0.009861764,0.003506853],"genre_scores_gemma":[0.7269532,0.0009472904,0.2607147,0.000558916,0.0002185362,0.0003397383,0.004507573,0.0004930578,0.005266892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01395827,"threshold_uncertainty_score":0.02775407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03131823917913042,"score_gpt":0.2876436426709154,"score_spread":0.256325403491785,"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."}}