{"id":"W4381714234","doi":"10.48550/arxiv.2306.12245","title":"Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tsinghua Shenzhen International Graduate School; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"End-to-end principle; Labrador Retriever; Computer science; Task (project management); Reading (process); Entity linking; End user; Pipeline (software); Artificial intelligence; Knowledge base; World Wide Web; Engineering; Linguistics; Programming language; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0005619123,0.0002328298,0.0003463343,0.0004444297,0.0001876222,0.00008522886,0.001295642,0.0002656214,0.00002100164],"category_scores_gemma":[0.0001448383,0.0002991905,0.0002657519,0.0007200201,0.00005207435,0.0002530647,0.001638046,0.0005726741,0.00004052328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002050306,"about_ca_system_score_gemma":0.0002537777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003249067,"about_ca_topic_score_gemma":0.00008222258,"domain_scores_codex":[0.9979958,0.00009858435,0.0002721028,0.001112422,0.0001672477,0.0003538777],"domain_scores_gemma":[0.9983118,0.0003197579,0.0002794014,0.000773706,0.0001806148,0.0001347278],"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":[0.00002668546,0.00003987883,0.007863417,0.0001644212,0.0001186652,0.00004703365,0.000444989,0.8543719,0.0001284971,0.1352834,0.0001408414,0.00137022],"study_design_scores_gemma":[0.0003838313,0.0000636801,0.002500483,0.0002263689,0.00006101892,0.00000300368,0.00005265203,0.9331298,0.0006828551,0.05848733,0.00396158,0.0004474049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1355988,0.00002393439,0.8620287,0.0001948895,0.001196155,0.0002932352,0.00001603061,0.0002976453,0.0003506092],"genre_scores_gemma":[0.9854241,0.00003728851,0.01035137,0.00004800593,0.0001730625,0.000002319918,0.00002310404,0.00002330488,0.003917451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8516773,"threshold_uncertainty_score":0.999946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1349473772410979,"score_gpt":0.2216361113038582,"score_spread":0.08668873406276037,"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."}}