{"id":"W4389519429","doi":"10.18653/v1/2023.emnlp-main.715","title":"mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Inference; Transformer; Natural language processing; Artificial intelligence; Task (project management); Language model; Simple (philosophy); Training set; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007782202,0.0001994029,0.0002353821,0.0002395082,0.0001344214,0.0001838037,0.001001065,0.0001017602,0.00001348437],"category_scores_gemma":[0.0005642228,0.0001817652,0.00009138218,0.001622526,0.00002412604,0.0002505241,0.0008197235,0.0001983466,0.0006018259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008350616,"about_ca_system_score_gemma":0.00008342688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009160028,"about_ca_topic_score_gemma":0.000006204055,"domain_scores_codex":[0.9977621,0.00009548227,0.0002624245,0.0007945434,0.0005313819,0.0005540233],"domain_scores_gemma":[0.9984358,0.0003260033,0.00004672679,0.0008405695,0.0001172351,0.0002336879],"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":[0.0006294964,0.0009224043,0.007076955,0.0003450146,0.0003653277,0.0006858472,0.03986822,0.08371242,0.02629093,0.1448701,0.08293758,0.6122957],"study_design_scores_gemma":[0.0007420208,0.0001586138,0.002363171,0.00001536185,0.000008101357,0.00002905961,0.0001414448,0.9733194,0.01467885,0.004415273,0.003683103,0.0004455801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3129091,0.00001413638,0.6803536,0.0002058222,0.0003672166,0.0005390084,0.000003746474,0.0008325305,0.004774888],"genre_scores_gemma":[0.9221801,0.000002083047,0.0749914,0.0006720281,0.00009181741,0.00002415872,0.000007235429,0.0000197813,0.002011462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.889607,"threshold_uncertainty_score":0.7735456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0394008374428256,"score_gpt":0.2952019718958999,"score_spread":0.2558011344530743,"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."}}