{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"deepmipt/diff_beam_search","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"deepmipt/expected_bleu","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3ca0baf0a82267c19593b2b0355e4b0d6247f615e1b61d0c7fc1e85bf8261d01","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}