{"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/multilingual-neural-machine-translation-with-1","title":"Multilingual Neural Machine Translation With Soft Decoupled Encoding","arxiv_id":"1902.03499","date":"2019-02-09","proceeding":"ICLR 2019 5","authors":["Xinyi Wang","Hieu Pham","Philip Arthur","Graham Neubig"],"abstract":"Multilingual training of neural machine translation (NMT) systems has led to\nimpressive accuracy improvements on low-resource languages. However, there are\nstill significant challenges in efficiently learning word representations in\nthe face of paucity of data. In this paper, we propose Soft Decoupled Encoding\n(SDE), a multilingual lexicon encoding framework specifically designed to share\nlexical-level information intelligently without requiring heuristic\npreprocessing such as pre-segmenting the data. SDE represents a word by its\nspelling through a character encoding, and its semantic meaning through a\nlatent embedding space shared by all languages. Experiments on a standard\ndataset of four low-resource languages show consistent improvements over strong\nmultilingual NMT baselines, with gains of up to 2 BLEU on one of the tested\nlanguages, achieving the new state-of-the-art on all four language pairs.","url_abs":"http://arxiv.org/abs/1902.03499v1","url_pdf":"http://arxiv.org/pdf/1902.03499v1.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":"multilingual-neural-machine-translation-with-1","repo_url":"https://github.com/cindyxinyiwang/SDE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.03499","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}