{"id":"W4361193744","doi":"10.48550/arxiv.2303.14979","title":"Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relevance (law); Artificial intelligence; Lexicon; Generator (circuit theory); Training set; Labeled data; Natural language processing; Information retrieval; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005997346,0.0004278903,0.0004673472,0.000359166,0.0003769752,0.0002095638,0.002725402,0.0004191408,0.00001121014],"category_scores_gemma":[0.0003557067,0.000540336,0.0003626434,0.0008325124,0.00008232333,0.0002384402,0.001754746,0.0008905613,0.0001825162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002567233,"about_ca_system_score_gemma":0.0006279382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002260542,"about_ca_topic_score_gemma":0.00004310496,"domain_scores_codex":[0.9969485,0.0001569125,0.0003317183,0.001811188,0.0001551659,0.0005965467],"domain_scores_gemma":[0.996744,0.000710082,0.0003255829,0.001662307,0.0003107896,0.0002472124],"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":[0.0002338515,0.0003223454,0.001194511,0.000407483,0.0004988448,0.000174415,0.01181601,0.8486493,0.002861479,0.124719,0.0002260253,0.008896745],"study_design_scores_gemma":[0.001037922,0.00006077423,0.001353397,0.00006774448,0.00007666912,0.000002280034,0.00018188,0.9720038,0.0008204256,0.02366012,0.0001706231,0.0005644324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.434102,0.000009095304,0.5628383,0.000228309,0.0004492993,0.0006697125,0.00002875537,0.001432484,0.0002420409],"genre_scores_gemma":[0.9318708,0.00002354887,0.06671906,0.00008931252,0.0001783903,0.00001005978,0.0000568422,0.00006090443,0.0009911224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4977688,"threshold_uncertainty_score":0.9997048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1457918079473519,"score_gpt":0.2567737515440782,"score_spread":0.1109819435967263,"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."}}