{"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/plan-attend-generate-character-level-neural-1","title":"Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder","arxiv_id":"1706.05087","date":"2017-06-13","proceeding":null,"authors":["Caglar Gulcehre","Francis Dutil","Adam Trischler","Yoshua Bengio"],"abstract":"We investigate the integration of a planning mechanism into an\nencoder-decoder architecture with an explicit alignment for character-level\nmachine translation. We develop a model that plans ahead when it computes\nalignments between the source and target sequences, constructing a matrix of\nproposed future alignments and a commitment vector that governs whether to\nfollow or recompute the plan. This mechanism is inspired by the strategic\nattentive reader and writer (STRAW) model. Our proposed model is end-to-end\ntrainable with fully differentiable operations. We show that it outperforms a\nstrong baseline on three character-level decoder neural machine translation on\nWMT'15 corpus. Our analysis demonstrates that our model can compute\nqualitatively intuitive alignments and achieves superior performance with fewer\nparameters.","url_abs":"http://arxiv.org/abs/1706.05087v2","url_pdf":"http://arxiv.org/pdf/1706.05087v2.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":"plan-attend-generate-character-level-neural-1","repo_url":"https://github.com/nyu-dl/dl4mt-cdec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.05087","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}