{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710554,0.0001943916,0.0002090422,0.0001233989,0.0004572501,0.0002891906,0.0004226067,0.00009488405,0.00001420132],"category_scores_gemma":[0.00004303157,0.0001874766,0.00006769196,0.0003964973,0.00004560346,0.0004835159,0.0000129711,0.0002097818,0.000003863895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005713895,"about_ca_system_score_gemma":0.0002644576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003095899,"about_ca_topic_score_gemma":0.0001602308,"domain_scores_codex":[0.9983218,0.00006385812,0.0002869546,0.0007027615,0.0002927456,0.0003318706],"domain_scores_gemma":[0.9990525,0.0001069176,0.00007456869,0.0005254228,0.0001163692,0.000124183],"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":[0.00004455054,0.0001261548,0.000002377951,0.0001180973,0.00003315768,0.0000432959,0.007242155,0.00803964,0.02642925,0.000107031,0.00001055611,0.9578037],"study_design_scores_gemma":[0.001190013,0.00008407826,0.00001561076,0.00009710516,0.00005010399,0.0001013927,0.002299693,0.8715712,0.1229782,0.0005424983,0.000709707,0.0003603743],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03801741,0.001244288,0.9586217,0.001198717,0.0003163082,0.0002714346,0.00006907507,0.0001419955,0.0001190235],"genre_scores_gemma":[0.5721756,0.00004123945,0.4271534,0.0003094812,0.00009233156,0.00001790717,0.00004192314,0.00001624098,0.000151904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9574434,"threshold_uncertainty_score":0.7645072,"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."}}