{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pre-training-of-deep-contextualized","title":"Global Entity Disambiguation with BERT","arxiv_id":"1909.00426","date":"2019-09-01","proceeding":"NAACL 2022 7","authors":["Ikuya Yamada","Koki Washio","Hiroyuki Shindo","Yuji Matsumoto"],"abstract":"We propose a global entity disambiguation (ED) model based on BERT. To capture global contextual information for ED, our model treats not only words but also entities as input tokens, and solves the task by sequentially resolving mentions to their referent entities and using resolved entities as inputs at each step. We train the model using a large entity-annotated corpus obtained from Wikipedia. We achieve new state-of-the-art results on five standard ED datasets: AIDA-CoNLL, MSNBC, AQUAINT, ACE2004, and WNED-WIKI. The source code and model checkpoint are available at https://github.com/studio-ousia/luke.","url_abs":"https://arxiv.org/abs/1909.00426v5","url_pdf":"https://arxiv.org/pdf/1909.00426v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pre-training-of-deep-contextualized","repo_url":"https://github.com/studio-ousia/luke","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/entity-disambiguation-on-ace2004","task":"Entity Disambiguation","dataset":"ACE2004","model":"confidence-order","rank_in_archive_order":2,"of":6,"metrics":{"Micro-F1":"91.9"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-aida-conll","task":"Entity Disambiguation","dataset":"AIDA-CoNLL","model":"confidence-order","rank_in_archive_order":1,"of":20,"metrics":{"In-KB Accuracy":"95.0"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-aquaint","task":"Entity Disambiguation","dataset":"AQUAINT","model":"confidence-order","rank_in_archive_order":1,"of":6,"metrics":{"Micro-F1":"93.5"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-msnbc","task":"Entity Disambiguation","dataset":"MSNBC","model":"confidence-order","rank_in_archive_order":1,"of":6,"metrics":{"Micro-F1":"96.3"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-wned-cweb","task":"Entity Disambiguation","dataset":"WNED-CWEB","model":"confidence-order","rank_in_archive_order":2,"of":7,"metrics":{"Micro-F1":"78.9"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-wned-cweb","task":"Entity Disambiguation","dataset":"WNED-CWEB","model":"MEP","rank_in_archive_order":6,"of":7,"metrics":{"Micro-F1":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-wned-wiki","task":"Entity Disambiguation","dataset":"WNED-WIKI","model":"confidence-order","rank_in_archive_order":2,"of":7,"metrics":{"Micro-F1":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-wned-wiki","task":"Entity Disambiguation","dataset":"WNED-WIKI","model":"MEP","rank_in_archive_order":5,"of":7,"metrics":{"Micro-F1":"86.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.00426","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}