{"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/bag-of-words-as-target-for-neural-machine","title":"Bag-of-Words as Target for Neural Machine Translation","arxiv_id":"1805.04871","date":"2018-05-13","proceeding":"ACL 2018 7","authors":["Shuming Ma","Xu sun","Yizhong Wang","Junyang Lin"],"abstract":"A sentence can be translated into more than one correct sentences. However,\nmost of the existing neural machine translation models only use one of the\ncorrect translations as the targets, and the other correct sentences are\npunished as the incorrect sentences in the training stage. Since most of the\ncorrect translations for one sentence share the similar bag-of-words, it is\npossible to distinguish the correct translations from the incorrect ones by the\nbag-of-words. In this paper, we propose an approach that uses both the\nsentences and the bag-of-words as targets in the training stage, in order to\nencourage the model to generate the potentially correct sentences that are not\nappeared in the training set. We evaluate our model on a Chinese-English\ntranslation dataset, and experiments show our model outperforms the strong\nbaselines by the BLEU score of 4.55.","url_abs":"http://arxiv.org/abs/1805.04871v1","url_pdf":"http://arxiv.org/pdf/1805.04871v1.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":"bag-of-words-as-target-for-neural-machine","repo_url":"https://github.com/lancopku/bag-of-words","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.04871","atlas_url":"https://app.syntology.ai/?focus=1805.04871","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}