{"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/neural-cross-lingual-entity-linking","title":"Neural Cross-Lingual Entity Linking","arxiv_id":"1712.01813","date":"2017-12-05","proceeding":null,"authors":["Avirup Sil","Gourab Kundu","Radu Florian","Wael Hamza"],"abstract":"A major challenge in Entity Linking (EL) is making effective use of\ncontextual information to disambiguate mentions to Wikipedia that might refer\nto different entities in different contexts. The problem exacerbates with\ncross-lingual EL which involves linking mentions written in non-English\ndocuments to entries in the English Wikipedia: to compare textual clues across\nlanguages we need to compute similarity between textual fragments across\nlanguages. In this paper, we propose a neural EL model that trains fine-grained\nsimilarities and dissimilarities between the query and candidate document from\nmultiple perspectives, combined with convolution and tensor networks. Further,\nwe show that this English-trained system can be applied, in zero-shot learning,\nto other languages by making surprisingly effective use of multi-lingual\nembeddings. The proposed system has strong empirical evidence yielding\nstate-of-the-art results in English as well as cross-lingual: Spanish and\nChinese TAC 2015 datasets.","url_abs":"http://arxiv.org/abs/1712.01813v1","url_pdf":"http://arxiv.org/pdf/1712.01813v1.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":[],"tasks":[{"task_slug":"cross-lingual-entity-linking","task_name":"Cross-Lingual Entity Linking"},{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"tensor-networks","task_name":"Tensor Networks"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/entity-disambiguation-on-aida-conll","task":"Entity Disambiguation","dataset":"AIDA-CoNLL","model":"This work+CtxLSTMs+LDC+MPCM","rank_in_archive_order":7,"of":20,"metrics":{"In-KB Accuracy":"94.0"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-tac2010","task":"Entity Disambiguation","dataset":"TAC2010","model":"This work+CtxLSTMs+LDC+MPCM","rank_in_archive_order":3,"of":4,"metrics":{"Micro Precision":"87.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.01813","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}