{"id":"W4317897852","doi":"10.1162/tacl_a_00539","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Naturalness; Natural language processing; Machine translation; Artificial intelligence; Modular design; Process (computing); Annotation; Benchmark (surveying); Information retrieval; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006989128,0.0001139956,0.0001445339,0.0001499214,0.0004317446,0.0001122431,0.0004639575,0.00009921613,0.000004669763],"category_scores_gemma":[0.001435833,0.0001104772,0.0001404615,0.0005200891,0.00002867721,0.00009701087,0.00002126347,0.0001133921,0.00001611472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001895357,"about_ca_system_score_gemma":0.0002098957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004506791,"about_ca_topic_score_gemma":0.00002749934,"domain_scores_codex":[0.9984911,0.00007447293,0.0004742575,0.000259493,0.000514315,0.0001863461],"domain_scores_gemma":[0.9974161,0.000776443,0.0003753901,0.0003241775,0.001069715,0.00003815059],"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":[0.000005464336,0.00004807421,0.0008398361,0.00001767083,0.00003310909,1.44373e-7,0.0001113698,0.9836686,0.00007932082,0.01307408,0.0006838621,0.001438458],"study_design_scores_gemma":[0.0005223511,0.00002858853,0.001946123,0.000008184677,0.00003624488,3.387149e-7,0.000003605207,0.9784149,0.001056815,0.01331233,0.004559529,0.0001110164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002890198,0.000005653244,0.9924868,0.00064392,0.002102212,0.0003089657,0.001319559,0.0001523014,0.00009041908],"genre_scores_gemma":[0.9277753,0.000001261543,0.06892978,0.0001469178,0.00045218,0.0000352077,0.002279399,0.0000136869,0.0003662142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9248852,"threshold_uncertainty_score":0.450513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03988226869889792,"score_gpt":0.3194351972184415,"score_spread":0.2795529285195436,"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."}}