{"id":"W4389520153","doi":"10.18653/v1/2023.findings-emnlp.392","title":"Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Korea Evaluation Institute of Industrial Technology; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy; Seoul National University; Hanyang University","keywords":"Domain adaptation; Computer science; Robustness (evolution); Leverage (statistics); Artificial intelligence; Testbed; Generalizability theory; Adaptation (eye); Viewpoints; Machine learning; Benchmark (surveying); Natural language processing; Human–computer interaction; Cartography","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":[0.0004296921,0.00005685129,0.00008632811,0.0001618229,0.00006544437,0.00003395831,0.0002055794,0.00003376738,0.00001519328],"category_scores_gemma":[0.00008008541,0.00005788798,0.00004042095,0.0006323927,0.00002296938,0.0002718987,0.0000549207,0.00005131329,0.00001740091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004227509,"about_ca_system_score_gemma":0.00007635431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002797905,"about_ca_topic_score_gemma":0.0000534342,"domain_scores_codex":[0.9992864,0.00003547143,0.0001738172,0.0001729757,0.0001680597,0.0001632386],"domain_scores_gemma":[0.999512,0.0002255358,0.0000606396,0.0001027129,0.00006270135,0.00003643202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002724187,0.00003530028,0.001268179,0.00001729382,0.000008529414,0.000005522987,0.00207874,0.1416738,0.00103692,0.8451903,0.0003505165,0.008307616],"study_design_scores_gemma":[0.0007602627,0.00003949375,0.02262333,0.00001728564,0.00000124306,4.875559e-7,0.001160239,0.9649498,0.000163358,0.008335671,0.001861852,0.00008692535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02810386,0.000006886704,0.9697455,0.0006671515,0.0001165833,0.0001174055,0.000006424706,0.0001016875,0.001134544],"genre_scores_gemma":[0.8500302,0.000002748889,0.1494962,0.00003864727,0.00001775303,0.000008713607,0.00004905264,0.000003887481,0.0003528614],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8368546,"threshold_uncertainty_score":0.2360603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04723287929223613,"score_gpt":0.2601785977514434,"score_spread":0.2129457184592073,"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."}}