{"id":"W4200635123","doi":"10.18653/v1/2022.naacl-main.168","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Deutsche Forschungsgemeinschaft","keywords":"Generative grammar; Computer science; Domain (mathematical analysis); Natural language processing; Artificial intelligence; Adaptation (eye); Domain adaptation; Mathematics; Psychology; Neuroscience","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":[0.0006709064,0.0001525241,0.0003599873,0.0001397125,0.0004165643,0.00002819801,0.002133498,0.00004176646,0.000001986625],"category_scores_gemma":[0.003479402,0.0001102755,0.0002556581,0.0005375574,0.0002787284,0.00005622017,0.001000382,0.0002125019,6.049765e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001483405,"about_ca_system_score_gemma":0.0001215044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007689667,"about_ca_topic_score_gemma":0.00002975208,"domain_scores_codex":[0.9981537,0.00003531783,0.0006295377,0.000270392,0.0007259073,0.0001851243],"domain_scores_gemma":[0.9947846,0.0003678258,0.002592051,0.0002982511,0.001944319,0.00001295143],"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":[0.0001888907,0.000192784,0.04530643,0.000319212,0.0004150788,1.385897e-7,0.01471451,0.1015929,0.0243579,0.8079301,0.000100781,0.004881325],"study_design_scores_gemma":[0.001996018,0.0008427315,0.01751349,0.0002259173,0.0002834682,0.000003412611,0.0207687,0.5686135,0.06752487,0.3213682,0.0002703879,0.0005893392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9696311,0.00009468987,0.02725866,0.00125591,0.0003579902,0.0009187479,0.0002934441,0.00008655826,0.0001028473],"genre_scores_gemma":[0.9432283,0.000003294161,0.05654755,0.00004362563,0.00003706987,0.00004553922,0.000006413206,0.0000125004,0.00007570468],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4865619,"threshold_uncertainty_score":0.4496905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02453907150408344,"score_gpt":0.2515881201371103,"score_spread":0.2270490486330269,"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."}}