{"id":"W3158658358","doi":"10.1109/taslp.2021.3074779","title":"GRTr: Generative-Retrieval Transformers for Data-Efficient Dialogue Domain Adaptation","year":2021,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Microsoft Research","keywords":"Computer science; Domain (mathematical analysis); Artificial intelligence; Adaptation (eye); Transformer; Generative grammar; Generative model; Information retrieval; Machine learning; Natural language processing; Mathematics; Engineering","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":[0.002814656,0.001395657,0.001402339,0.001337221,0.0006606833,0.001998413,0.004444061,0.001941018,0.02123065],"category_scores_gemma":[0.01098265,0.0009123076,0.002195818,0.001404335,0.001820534,0.004927278,0.004785152,0.003503877,0.01250243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386621,"about_ca_system_score_gemma":0.001314219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003171808,"about_ca_topic_score_gemma":0.003422556,"domain_scores_codex":[0.9981274,0.0006393832,0.0001238033,0.0005317505,0.0004233043,0.0001543988],"domain_scores_gemma":[0.9972254,0.001351382,0.0001268862,0.0008785098,0.0002930633,0.0001248996],"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":[0.0007982295,0.0003323984,0.0008382251,0.0005741155,0.000140459,0.0006197866,0.0006997831,0.1673203,0.02206589,0.2841491,0.05108242,0.4713792],"study_design_scores_gemma":[0.00006468775,0.00006829378,0.0001009637,0.00002126244,0.00003006401,0.0002320558,0.00004206708,0.8840294,0.007972575,0.09482344,0.01256979,0.00004542835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001390797,0.0001121762,0.9879488,0.000154165,0.00004621246,0.00008030402,0.0002966055,0.008085602,0.001885322],"genre_scores_gemma":[0.2422263,0.0004818778,0.7309318,0.0008690428,0.0002428823,0.0005967087,0.002937356,0.005046703,0.01666726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02123065,"threshold_uncertainty_score":0.07102358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04292352133080539,"score_gpt":0.2921916199794125,"score_spread":0.2492680986486071,"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."}}