{"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/zero-shot-neural-transfer-for-cross-lingual","title":"Zero-shot Neural Transfer for Cross-lingual Entity Linking","arxiv_id":"1811.04154","date":"2018-11-09","proceeding":null,"authors":["Shruti Rijhwani","Jiateng Xie","Graham Neubig","Jaime Carbonell"],"abstract":"Cross-lingual entity linking maps an entity mention in a source language to\nits corresponding entry in a structured knowledge base that is in a different\n(target) language. While previous work relies heavily on bilingual lexical\nresources to bridge the gap between the source and the target languages, these\nresources are scarce or unavailable for many low-resource languages. To address\nthis problem, we investigate zero-shot cross-lingual entity linking, in which\nwe assume no bilingual lexical resources are available in the source\nlow-resource language. Specifically, we propose pivot-based entity linking,\nwhich leverages information from a high-resource \"pivot\" language to train\ncharacter-level neural entity linking models that are transferred to the source\nlow-resource language in a zero-shot manner. With experiments on 9 low-resource\nlanguages and transfer through a total of 54 languages, we show that our\nproposed pivot-based framework improves entity linking accuracy 17% (absolute)\non average over the baseline systems, for the zero-shot scenario. Further, we\nalso investigate the use of language-universal phonological representations\nwhich improves average accuracy (absolute) by 36% when transferring between\nlanguages that use different scripts.","url_abs":"http://arxiv.org/abs/1811.04154v1","url_pdf":"http://arxiv.org/pdf/1811.04154v1.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":"zero-shot-neural-transfer-for-cross-lingual","repo_url":"https://github.com/neulab/pivot-based-entity-linking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"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":{"atlas_url":"https://app.syntology.ai/?focus=1811.04154","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}