{"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/minimum-risk-training-for-neural-machine","title":"Minimum Risk Training for Neural Machine Translation","arxiv_id":"1512.02433","date":"2015-12-08","proceeding":"ACL 2016 8","authors":["Shiqi Shen","Yong Cheng","Zhongjun He","wei he","Hua Wu","Maosong Sun","Yang Liu"],"abstract":"We propose minimum risk training for end-to-end neural machine translation.\nUnlike conventional maximum likelihood estimation, minimum risk training is\ncapable of optimizing model parameters directly with respect to arbitrary\nevaluation metrics, which are not necessarily differentiable. Experiments show\nthat our approach achieves significant improvements over maximum likelihood\nestimation on a state-of-the-art neural machine translation system across\nvarious languages pairs. Transparent to architectures, our approach can be\napplied to more neural networks and potentially benefit more NLP tasks.","url_abs":"http://arxiv.org/abs/1512.02433v3","url_pdf":"http://arxiv.org/pdf/1512.02433v3.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":"minimum-risk-training-for-neural-machine","repo_url":"https://github.com/kh-kim/simple-nmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1512.02433","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}