{"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/exploiting-similarities-among-languages-for","title":"Exploiting Similarities among Languages for Machine Translation","arxiv_id":"1309.4168","date":"2013-09-17","proceeding":null,"authors":["Tomas Mikolov","Quoc V. Le","Ilya Sutskever"],"abstract":"Dictionaries and phrase tables are the basis of modern statistical machine\ntranslation systems. This paper develops a method that can automate the process\nof generating and extending dictionaries and phrase tables. Our method can\ntranslate missing word and phrase entries by learning language structures based\non large monolingual data and mapping between languages from small bilingual\ndata. It uses distributed representation of words and learns a linear mapping\nbetween vector spaces of languages. Despite its simplicity, our method is\nsurprisingly effective: we can achieve almost 90% precision@5 for translation\nof words between English and Spanish. This method makes little assumption about\nthe languages, so it can be used to extend and refine dictionaries and\ntranslation tables for any language pairs.","url_abs":"http://arxiv.org/abs/1309.4168v1","url_pdf":"http://arxiv.org/pdf/1309.4168v1.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":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/Babylonpartners/fastText_multilingual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/babylonhealth/fastText_multilingual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/big-o/transvec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/facebookresearch/MUSE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/jiajunhua/facebookresearch-MUSE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/selimseker/logogram-language-generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploiting-similarities-among-languages-for","repo_url":"https://github.com/tensorflow/models/tree/master/research/skip_thoughts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1309.4168","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}