{"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/robust-cross-lingual-hypernymy-detection","title":"Robust Cross-lingual Hypernymy Detection using Dependency Context","arxiv_id":"1803.11291","date":"2018-03-30","proceeding":"NAACL 2018 6","authors":["Shyam Upadhyay","Yogarshi Vyas","Marine Carpuat","Dan Roth"],"abstract":"Cross-lingual Hypernymy Detection involves determining if a word in one\nlanguage (\"fruit\") is a hypernym of a word in another language (\"pomme\" i.e.\napple in French). The ability to detect hypernymy cross-lingually can aid in\nsolving cross-lingual versions of tasks such as textual entailment and event\ncoreference. We propose BISPARSE-DEP, a family of unsupervised approaches for\ncross-lingual hypernymy detection, which learns sparse, bilingual word\nembeddings based on dependency contexts. We show that BISPARSE-DEP can\nsignificantly improve performance on this task, compared to approaches based\nonly on lexical context. Our approach is also robust, showing promise for\nlow-resource settings: our dependency-based embeddings can be learned using a\nparser trained on related languages, with negligible loss in performance. We\nalso crowd-source a challenging dataset for this task on four languages --\nRussian, French, Arabic, and Chinese. Our embeddings and datasets are publicly\navailable.","url_abs":"http://arxiv.org/abs/1803.11291v1","url_pdf":"http://arxiv.org/pdf/1803.11291v1.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":"robust-cross-lingual-hypernymy-detection","repo_url":"https://github.com/yogarshi/bisparse-dep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.11291","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}