{"id":"W4385571887","doi":"10.18653/v1/2023.acl-long.180","title":"HistRED: A Historical Document-Level Relation Extraction Dataset","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Supercomputing Center, Korea Institute of Science and Technology Information; Defense Acquisition Program Administration; Korea Advanced Institute of Science and Technology; Agency for Defense Development; Korea University","keywords":"Computer science; Natural language processing; Relationship extraction; Robustness (evolution); Relation (database); Sentence; Artificial intelligence; Context (archaeology); Information retrieval; License; Information extraction; Data mining; History; Archaeology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008566378,0.001524381,0.0007466396,0.005478872,0.001218507,0.001141223,0.002049844,0.001820896,0.008294594],"category_scores_gemma":[0.003522436,0.0003747772,0.001022392,0.006240895,0.0004944034,0.001785561,0.001456751,0.001125235,0.0107776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001458487,"about_ca_system_score_gemma":0.001760972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01994704,"about_ca_topic_score_gemma":0.04843967,"domain_scores_codex":[0.9988837,0.0001709983,0.0001836758,0.0003716574,0.0002785175,0.0001114435],"domain_scores_gemma":[0.9981146,0.0004876207,0.0002113726,0.0005425037,0.0004823554,0.0001616362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004302529,0.0004288756,0.01187407,0.002565136,0.0001726161,0.001107465,0.0003986197,0.002120062,0.005791422,0.002499336,0.906482,0.06613009],"study_design_scores_gemma":[0.0002668537,0.0001704357,0.0386249,0.0003291331,0.0001407241,0.001465862,0.001012418,0.009293002,0.009111539,0.002291287,0.9371782,0.0001157307],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02191702,0.001629259,0.00241828,0.0005216435,0.0001707853,0.0001858945,0.9636011,0.004056857,0.005499244],"genre_scores_gemma":[0.009826916,0.0002303138,0.005863031,0.0001279232,0.00002539266,0.000131617,0.9818304,0.00007927918,0.001885029],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01994704,"threshold_uncertainty_score":0.03966188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04333989060999734,"score_gpt":0.3219132920197142,"score_spread":0.2785734014097169,"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."}}