{"id":"W4390640268","doi":"10.1016/j.neucom.2023.127219","title":"Dual-space Hierarchical Learning for Goal-guided Conversational Recommendation","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Bureau of Education of Guangzhou Municipality; National Natural Science Foundation of China; National Institutes of Health; National Science Foundation","keywords":"Computer science; Leverage (statistics); Dialog box; Exploit; Artificial intelligence; Space (punctuation); Representation (politics); Feature learning; Recommender system; Machine learning; Dual (grammatical number); Context (archaeology); Focus (optics); World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.0006584658,0.0001439067,0.0001503409,0.0001660799,0.0002526143,0.0005078044,0.0002610923,0.00006346955,0.00001167174],"category_scores_gemma":[0.00008469519,0.0001409943,0.0001048316,0.0002943248,0.00001509368,0.0003719489,0.0002069072,0.0003006788,0.00002197034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005520801,"about_ca_system_score_gemma":0.00006465369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001247279,"about_ca_topic_score_gemma":6.826537e-7,"domain_scores_codex":[0.9985841,0.0001362694,0.0003164423,0.0005179967,0.0001653032,0.0002798939],"domain_scores_gemma":[0.9989067,0.0007099036,0.00007935159,0.0001662194,0.00006893269,0.00006887182],"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":[0.000005668697,0.00004334694,0.0005893914,0.0002493372,0.00005018943,0.00002859744,0.001593539,0.0009284929,0.003526679,0.3627421,0.05579833,0.5744444],"study_design_scores_gemma":[0.000147519,0.00008129839,0.0002703916,0.00005920442,0.000003349465,0.00007627634,0.0000112368,0.726129,0.00116683,0.003888665,0.2680226,0.0001435888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003246489,0.00003891733,0.9808943,0.009892325,0.00120426,0.0003537504,0.000001099528,0.001275727,0.003093121],"genre_scores_gemma":[0.8986664,0.000006316829,0.09978493,0.0004960863,0.0005515094,0.00004906007,0.00001954499,0.00002625339,0.0003998842],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.89542,"threshold_uncertainty_score":0.574958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03140273871533487,"score_gpt":0.3004989408601543,"score_spread":0.2690962021448194,"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."}}