{"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-multilingual-supervision-for-cross","title":"Joint Multilingual Supervision for Cross-lingual Entity Linking","arxiv_id":"1809.07657","date":"2018-09-20","proceeding":"EMNLP 2018 10","authors":["Shyam Upadhyay","Nitish Gupta","Dan Roth"],"abstract":"Cross-lingual Entity Linking (XEL) aims to ground entity mentions written in\nany language to an English Knowledge Base (KB), such as Wikipedia. XEL for most\nlanguages is challenging, owing to limited availability of resources as\nsupervision. We address this challenge by developing the first XEL approach\nthat combines supervision from multiple languages jointly. This enables our\napproach to: (a) augment the limited supervision in the target language with\nadditional supervision from a high-resource language (like English), and (b)\ntrain a single entity linking model for multiple languages, improving upon\nindividually trained models for each language. Extensive evaluation on three\nbenchmark datasets across 8 languages shows that our approach significantly\nimproves over the current state-of-the-art. We also provide analyses in two\nlimited resource settings: (a) zero-shot setting, when no supervision in the\ntarget language is available, and in (b) low-resource setting, when some\nsupervision in the target language is available. Our analysis provides insights\ninto the limitations of zero-shot XEL approaches in realistic scenarios, and\nshows the value of joint supervision in low-resource settings.","url_abs":"http://arxiv.org/abs/1809.07657v1","url_pdf":"http://arxiv.org/pdf/1809.07657v1.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-multilingual-supervision-for-cross","repo_url":"https://github.com/shyamupa/xelms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"cross-lingual-entity-linking","task_name":"Cross-Lingual Entity Linking"},{"task_slug":"entity-linking","task_name":"Entity Linking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.07657","atlas_url":"https://app.syntology.ai/?focus=1809.07657","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}