{"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/character-level-chinese-english-translation","title":"Character-level Chinese-English Translation through ASCII Encoding","arxiv_id":"1805.03330","date":"2018-05-09","proceeding":"WS 2018 10","authors":["Nikola I. Nikolov","Yuhuang Hu","Mi Xue Tan","Richard H. R. Hahnloser"],"abstract":"Character-level Neural Machine Translation (NMT) models have recently\nachieved impressive results on many language pairs. They mainly do well for\nIndo-European language pairs, where the languages share the same writing\nsystem. However, for translating between Chinese and English, the gap between\nthe two different writing systems poses a major challenge because of a lack of\nsystematic correspondence between the individual linguistic units. In this\npaper, we enable character-level NMT for Chinese, by breaking down Chinese\ncharacters into linguistic units similar to that of Indo-European languages. We\nuse the Wubi encoding scheme, which preserves the original shape and semantic\ninformation of the characters, while also being reversible. We show promising\nresults from training Wubi-based models on the character- and subword-level\nwith recurrent as well as convolutional models.","url_abs":"http://arxiv.org/abs/1805.03330v2","url_pdf":"http://arxiv.org/pdf/1805.03330v2.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":"character-level-chinese-english-translation","repo_url":"https://github.com/duguyue100/wmt-en2wubi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":{"atlas_url":"https://app.syntology.ai/?focus=1805.03330","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}