{"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/better-translation-for-vietnamese","title":"Better Translation for Vietnamese","arxiv_id":null,"date":"2021-04-20","proceeding":null,"authors":["Chinh Ngo","Trieu Trinh"],"abstract":"We collect data from open sources on the Internet, and classify them into different categories, each labeled with a specific language style 3. In total, there are 3.3 million pairs of English and Vietnamese texts, ranging from single sentences to paragraphs. A model trained with our dataset outperforms Google Translate on a selected set of diverse text sources. On IWSLT'15 we achieved a BLEU score of 37.84.","url_abs":"https://blog.vietai.org/sat/","url_pdf":"https://blog.vietai.org/sat/","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":"better-translation-for-vietnamese","repo_url":"https://github.com/vietai/mTet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-english-1","task":"Machine Translation","dataset":"IWSLT2015 English-Vietnamese","model":"Tall Transformer with Style-Augmented Training","rank_in_archive_order":2,"of":11,"metrics":{"BLEU":"37.8"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}