{"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/deconvolution-based-global-decoding-for","title":"Deconvolution-Based Global Decoding for Neural Machine Translation","arxiv_id":"1806.03692","date":"2018-06-10","proceeding":"COLING 2018 8","authors":["Junyang Lin","Xu sun","Xuancheng Ren","Shuming Ma","Jinsong Su","Qi Su"],"abstract":"A great proportion of sequence-to-sequence (Seq2Seq) models for Neural\nMachine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate\ntranslation word by word following a sequential order. As the studies of\nlinguistics have proved that language is not linear word sequence but sequence\nof complex structure, translation at each step should be conditioned on the\nwhole target-side context. To tackle the problem, we propose a new NMT model\nthat decodes the sequence with the guidance of its structural prediction of the\ncontext of the target sequence. Our model generates translation based on the\nstructural prediction of the target-side context so that the translation can be\nfreed from the bind of sequential order. Experimental results demonstrate that\nour model is more competitive compared with the state-of-the-art methods, and\nthe analysis reflects that our model is also robust to translating sentences of\ndifferent lengths and it also reduces repetition with the instruction from the\ntarget-side context for decoding.","url_abs":"http://arxiv.org/abs/1806.03692v1","url_pdf":"http://arxiv.org/pdf/1806.03692v1.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":"deconvolution-based-global-decoding-for","repo_url":"https://github.com/lancopku/DeconvDec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-english-1","task":"Machine Translation","dataset":"IWSLT2015 English-Vietnamese","model":"DeconvDec","rank_in_archive_order":9,"of":11,"metrics":{"BLEU":"28.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03692","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}