{"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/differentiable-lower-bound-for-expected-bleu","title":"Differentiable lower bound for expected BLEU score","arxiv_id":"1712.04708","date":"2017-12-13","proceeding":null,"authors":["Vlad Zhukov","Eugene Golikov","Maksim Kretov"],"abstract":"In natural language processing tasks performance of the models is often\nmeasured with some non-differentiable metric, such as BLEU score. To use\nefficient gradient-based methods for optimization, it is a common workaround to\noptimize some surrogate loss function. This approach is effective if\noptimization of such loss also results in improving target metric. The\ncorresponding problem is referred to as loss-evaluation mismatch. In the\npresent work we propose a method for calculation of differentiable lower bound\nof expected BLEU score that does not involve computationally expensive sampling\nprocedure such as the one required when using REINFORCE rule from reinforcement\nlearning (RL) framework.","url_abs":"http://arxiv.org/abs/1712.04708v4","url_pdf":"http://arxiv.org/pdf/1712.04708v4.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":"differentiable-lower-bound-for-expected-bleu","repo_url":"https://github.com/deepmipt/diff_beam_search/tree/master/expected_bleu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"differentiable-lower-bound-for-expected-bleu","repo_url":"https://github.com/deepmipt/expected_bleu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"reinforce","method_name":"REINFORCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}