{"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/mtet-multi-domain-translation-for-english-and","title":"MTet: Multi-domain Translation for English and Vietnamese","arxiv_id":"2210.05610","date":"2022-10-11","proceeding":null,"authors":["Chinh Ngo","Trieu H. Trinh","Long Phan","Hieu Tran","Tai Dang","Hieu Nguyen","Minh Nguyen","Minh-Thang Luong"],"abstract":"We introduce MTet, the largest publicly available parallel corpus for English-Vietnamese translation. MTet consists of 4.2M high-quality training sentence pairs and a multi-domain test set refined by the Vietnamese research community. Combining with previous works on English-Vietnamese translation, we grow the existing parallel dataset to 6.2M sentence pairs. We also release the first pretrained model EnViT5 for English and Vietnamese languages. Combining both resources, our model significantly outperforms previous state-of-the-art results by up to 2 points in translation BLEU score, while being 1.6 times smaller.","url_abs":"https://arxiv.org/abs/2210.05610v2","url_pdf":"https://arxiv.org/pdf/2210.05610v2.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":"mtet-multi-domain-translation-for-english-and","repo_url":"https://github.com/vietai/mTet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"mtet-multi-domain-translation-for-english-and","repo_url":"https://github.com/vietai/SAT","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-english-1","task":"Machine Translation","dataset":"IWSLT2015 English-Vietnamese","model":"EnViT5 + MTet","rank_in_archive_order":1,"of":11,"metrics":{"BLEU":"40.2"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.05610","atlas_url":"https://app.syntology.ai/?focus=2210.05610","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}