{"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/joint-learning-of-the-embedding-of-words-and","title":"Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation","arxiv_id":"1601.01343","date":"2016-01-06","proceeding":"CONLL 2016 8","authors":["Ikuya Yamada","Hiroyuki Shindo","Hideaki Takeda","Yoshiyasu Takefuji"],"abstract":"Named Entity Disambiguation (NED) refers to the task of resolving multiple\nnamed entity mentions in a document to their correct references in a knowledge\nbase (KB) (e.g., Wikipedia). In this paper, we propose a novel embedding method\nspecifically designed for NED. The proposed method jointly maps words and\nentities into the same continuous vector space. We extend the skip-gram model\nby using two models. The KB graph model learns the relatedness of entities\nusing the link structure of the KB, whereas the anchor context model aims to\nalign vectors such that similar words and entities occur close to one another\nin the vector space by leveraging KB anchors and their context words. By\ncombining contexts based on the proposed embedding with standard NED features,\nwe achieved state-of-the-art accuracy of 93.1% on the standard CoNLL dataset\nand 85.2% on the TAC 2010 dataset.","url_abs":"http://arxiv.org/abs/1601.01343v4","url_pdf":"http://arxiv.org/pdf/1601.01343v4.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":"joint-learning-of-the-embedding-of-words-and","repo_url":"https://github.com/wikipedia2vec/wikipedia2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"entity-linking","task_name":"Entity Linking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/entity-disambiguation-on-aida-conll","task":"Entity Disambiguation","dataset":"AIDA-CoNLL","model":"Wikipedia2Vec-GBRT","rank_in_archive_order":11,"of":20,"metrics":{"In-KB Accuracy":"93.1"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-aida-conll","task":"Entity Disambiguation","dataset":"AIDA-CoNLL","model":"Wikipedia2Vec","rank_in_archive_order":15,"of":20,"metrics":{"In-KB Accuracy":"91.5"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-tac2010","task":"Entity Disambiguation","dataset":"TAC2010","model":"Wikipedia2Vec","rank_in_archive_order":4,"of":4,"metrics":{"Micro Precision":"85.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1601.01343","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}