{"id":"W4283792637","doi":"10.1609/aaai.v36i11.21591","title":"Multi-Dimension Attention for Multi-Turn Dialog Generation (Student Abstract)","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Dialog box; Dimension (graph theory); Computer science; Generative grammar; Scope (computer science); Generative model; Artificial intelligence; Process (computing); Dialog system; Natural language processing; Semantic interpretation; Speech recognition; Programming language; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00124954,0.000542154,0.0005051647,0.0004599057,0.0003700898,0.0006245738,0.001052411,0.0009907396,0.003101193],"category_scores_gemma":[0.00271896,0.0003466706,0.0009106671,0.0003859552,0.0005719589,0.0009600231,0.001213995,0.001517563,0.0005154595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009334032,"about_ca_system_score_gemma":0.0005642933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007739891,"about_ca_topic_score_gemma":0.008144091,"domain_scores_codex":[0.9996296,0.0001666001,0.00001271969,0.0001058907,0.00003410201,0.00005100342],"domain_scores_gemma":[0.9987671,0.0009202151,0.00005998671,0.00007709,0.000115973,0.00005960333],"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":[0.0003539876,0.0001736512,0.002330375,0.0001112466,0.000133147,0.0002471673,0.000493772,0.7728451,0.01167431,0.01842108,0.00315751,0.1900585],"study_design_scores_gemma":[0.000004511222,0.00001658737,0.0001964931,0.000002720938,0.000007072393,0.00001630005,0.0000050749,0.9955396,0.0005841331,0.003460331,0.0001622622,0.000004881605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1396907,0.0008964765,0.8526291,0.00103146,0.0001739516,0.00008875481,0.0002347382,0.00166067,0.003594099],"genre_scores_gemma":[0.9401259,0.0001880073,0.05493436,0.0002245888,0.00007664555,0.0001055828,0.0001903979,0.00009186823,0.004062757],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007739891,"threshold_uncertainty_score":0.01538968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2006134807242427,"score_gpt":0.3464957192817173,"score_spread":0.1458822385574746,"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."}}