{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001508769,0.0001630731,0.0002309069,0.0002107479,0.001173663,0.0001514917,0.0009229237,0.00005393505,0.00007037628],"category_scores_gemma":[0.003091128,0.0001555763,0.0001796221,0.0009180433,0.0000459853,0.0001144044,0.0005189026,0.0003389961,0.000008750399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006752394,"about_ca_system_score_gemma":0.0004108189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002318002,"about_ca_topic_score_gemma":0.000002787848,"domain_scores_codex":[0.9970789,0.0002683606,0.000520206,0.0004103025,0.001420644,0.0003015837],"domain_scores_gemma":[0.9965203,0.001375427,0.0008927069,0.0003148124,0.0008246159,0.0000721527],"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":[0.0002344363,0.000167369,0.007468721,0.00002067527,0.000215187,0.000003409269,0.002230561,0.3821816,0.0002433218,0.5900546,0.01713188,0.00004820948],"study_design_scores_gemma":[0.007911782,0.0008127652,0.03680103,0.00005395146,0.0001918586,0.000028886,0.001324801,0.3909236,0.0006153135,0.3293136,0.231078,0.0009443933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03454777,0.00005693357,0.9366372,0.007810151,0.007041763,0.002138213,0.0009139365,0.0003073683,0.01054666],"genre_scores_gemma":[0.9292976,0.000001364272,0.06561895,0.0005569895,0.0002588431,0.00006413947,0.0002740223,0.00002911087,0.003898984],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8947498,"threshold_uncertainty_score":0.9026982,"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."}}