{"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/learning-joint-multilingual-sentence","title":"Learning Joint Multilingual Sentence Representations with Neural Machine Translation","arxiv_id":"1704.04154","date":"2017-04-13","proceeding":"WS 2017 8","authors":["Holger Schwenk","Matthijs Douze"],"abstract":"In this paper, we use the framework of neural machine translation to learn\njoint sentence representations across six very different languages. Our aim is\nthat a representation which is independent of the language, is likely to\ncapture the underlying semantics. We define a new cross-lingual similarity\nmeasure, compare up to 1.4M sentence representations and study the\ncharacteristics of close sentences. We provide experimental evidence that\nsentences that are close in embedding space are indeed semantically highly\nrelated, but often have quite different structure and syntax. These relations\nalso hold when comparing sentences in different languages.","url_abs":"http://arxiv.org/abs/1704.04154v2","url_pdf":"http://arxiv.org/pdf/1704.04154v2.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":"learning-joint-multilingual-sentence","repo_url":"https://github.com/Unbabel/COMET","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"joint-multilingual-sentence-representations","task_name":"Joint Multilingual Sentence Representations"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.04154","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}