{"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/loss-in-translation-learning-bilingual-word","title":"Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion","arxiv_id":"1804.07745","date":"2018-04-20","proceeding":"EMNLP 2018 10","authors":["Armand Joulin","Piotr Bojanowski","Tomas Mikolov","Herve Jegou","Edouard Grave"],"abstract":"Continuous word representations learned separately on distinct languages can\nbe aligned so that their words become comparable in a common space. Existing\nworks typically solve a least-square regression problem to learn a rotation\naligning a small bilingual lexicon, and use a retrieval criterion for\ninference. In this paper, we propose an unified formulation that directly\noptimizes a retrieval criterion in an end-to-end fashion. Our experiments on\nstandard benchmarks show that our approach outperforms the state of the art on\nword translation, with the biggest improvements observed for distant language\npairs such as English-Chinese.","url_abs":"http://arxiv.org/abs/1804.07745v3","url_pdf":"http://arxiv.org/pdf/1804.07745v3.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":"loss-in-translation-learning-bilingual-word","repo_url":"https://github.com/Kelechukwu1/PidginUNMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"loss-in-translation-learning-bilingual-word","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":"loss-in-translation-learning-bilingual-word","repo_url":"https://github.com/keleog/PidginUNMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"loss-in-translation-learning-bilingual-word","repo_url":"https://github.com/facebookresearch/fastText/blob/master/docs/aligned-vectors.md","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-translation","task_name":"Word Translation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.07745","atlas_url":"https://app.syntology.ai/?focus=1804.07745","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}