{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005768458,0.00156011,0.0008414801,0.003025856,0.00195977,0.002244485,0.002667047,0.001548953,0.005085057],"category_scores_gemma":[0.01840143,0.0004998351,0.001604014,0.001702635,0.001114367,0.002856352,0.006356001,0.002460239,0.005129466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001149979,"about_ca_system_score_gemma":0.002050341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005742458,"about_ca_topic_score_gemma":0.01121709,"domain_scores_codex":[0.9924836,0.003042683,0.0007109788,0.002334582,0.001106025,0.0003222126],"domain_scores_gemma":[0.9879822,0.003635942,0.0005749054,0.003953732,0.003168021,0.0006852178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002467707,0.001741888,0.02037587,0.004620685,0.0005669213,0.001857074,0.0100999,0.02943067,0.06755533,0.01900468,0.3192295,0.5230498],"study_design_scores_gemma":[0.0005220053,0.0007840219,0.03279242,0.0008797183,0.0002811958,0.001466576,0.007717704,0.2236685,0.07518837,0.02057376,0.6355611,0.0005645612],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1761277,0.002719729,0.4918461,0.001997336,0.002347692,0.003719879,0.1904838,0.09455238,0.03620532],"genre_scores_gemma":[0.2140879,0.000299638,0.3621267,0.0005775226,0.0001696981,0.003712425,0.4091086,0.002900633,0.00701694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005768458,"threshold_uncertainty_score":0.03050691,"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."}}