{"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/english-japanese-neural-machine-translation","title":"English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor","arxiv_id":"1706.08198","date":"2017-06-26","proceeding":null,"authors":["Yukio Matsumura","Takayuki Sato","Mamoru Komachi"],"abstract":"Neural machine translation (NMT) has recently become popular in the field of\nmachine translation. However, NMT suffers from the problem of repeating or\nmissing words in the translation. To address this problem, Tu et al. (2017)\nproposed an encoder-decoder-reconstructor framework for NMT using\nback-translation. In this method, they selected the best forward translation\nmodel in the same manner as Bahdanau et al. (2015), and then trained a\nbi-directional translation model as fine-tuning. Their experiments show that it\noffers significant improvement in BLEU scores in Chinese-English translation\ntask. We confirm that our re-implementation also shows the same tendency and\nalleviates the problem of repeating and missing words in the translation on a\nEnglish-Japanese task too. In addition, we evaluate the effectiveness of\npre-training by comparing it with a jointly-trained model of forward\ntranslation and back-translation.","url_abs":"http://arxiv.org/abs/1706.08198v1","url_pdf":"http://arxiv.org/pdf/1706.08198v1.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":"english-japanese-neural-machine-translation","repo_url":"https://github.com/yukio326/reconstructor-nmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}