{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001663101,0.001610121,0.001577938,0.001652325,0.0007263339,0.001490772,0.004679477,0.001394846,0.01078529],"category_scores_gemma":[0.004835443,0.0009395835,0.001197354,0.001307311,0.0008548615,0.004300531,0.004241313,0.001773902,0.007937134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008957027,"about_ca_system_score_gemma":0.001902571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01057271,"about_ca_topic_score_gemma":0.0230189,"domain_scores_codex":[0.998966,0.0001845711,0.00006447655,0.0003842119,0.0002527332,0.0001481624],"domain_scores_gemma":[0.998753,0.0003931801,0.00005636149,0.0004806721,0.0002388747,0.00007802447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004781128,0.0003586835,0.001067377,0.000480213,0.0002389651,0.0002672008,0.0002908365,0.05426925,0.0436623,0.01008941,0.03652818,0.8522695],"study_design_scores_gemma":[0.00009451126,0.0002124233,0.0004699018,0.00002960245,0.00007508732,0.0003712581,0.0001255707,0.940486,0.02536398,0.01571396,0.01698841,0.00006931375],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01329575,0.0009901493,0.9441348,0.0001710439,0.0001764875,0.0002583594,0.000735914,0.03680479,0.003432654],"genre_scores_gemma":[0.2148071,0.0006161238,0.7634844,0.0007655173,0.0002006091,0.0004490298,0.005306071,0.003006891,0.01136423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01078529,"threshold_uncertainty_score":0.03608036,"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."}}