{"id":"W3206786886","doi":"10.18653/v1/2022.findings-acl.316","title":"Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Invariant (physics); Classifier (UML); Source code; Embedding; Adversarial system; Artificial intelligence; Encoder; Autoencoder; Theoretical computer science; Pattern recognition (psychology); Algorithm; Deep learning; Mathematics","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":[0.001718108,0.001094291,0.001365379,0.0006287016,0.000369049,0.0009073404,0.002249068,0.001440022,0.001910527],"category_scores_gemma":[0.004767039,0.0004048763,0.0007021881,0.0006744321,0.001096988,0.002965836,0.001835781,0.001861221,0.0009690588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009377407,"about_ca_system_score_gemma":0.0007937246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003816705,"about_ca_topic_score_gemma":0.004213269,"domain_scores_codex":[0.9991598,0.0002788957,0.00003578324,0.0002514094,0.0001779656,0.00009615626],"domain_scores_gemma":[0.9985297,0.0007499317,0.0001043781,0.0004278828,0.0001232251,0.00006493912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003703822,0.000299211,0.0011855,0.0001935789,0.0001225153,0.0001749783,0.0001183179,0.7372962,0.008420791,0.02093991,0.009501789,0.2213767],"study_design_scores_gemma":[0.00001213437,0.00005767493,0.0001016836,0.00000511494,0.000007126003,0.0000409028,0.000008968065,0.9915775,0.001395103,0.006324028,0.0004615951,0.000008216227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05794896,0.0009297201,0.9340972,0.0004616359,0.00008856666,0.0001472443,0.0003433411,0.003039991,0.002943286],"genre_scores_gemma":[0.8394619,0.0003885376,0.1493976,0.0006139449,0.0001313371,0.0001761514,0.001665701,0.0002188765,0.007946129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003816705,"threshold_uncertainty_score":0.009086311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01593641139419208,"score_gpt":0.2523305473785822,"score_spread":0.2363941359843901,"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."}}