{"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/an-efficient-character-level-neural-machine","title":"An Efficient Character-Level Neural Machine Translation","arxiv_id":"1608.04738","date":"2016-08-16","proceeding":null,"authors":["Shenjian Zhao","Zhihua Zhang"],"abstract":"Neural machine translation aims at building a single large neural network\nthat can be trained to maximize translation performance. The encoder-decoder\narchitecture with an attention mechanism achieves a translation performance\ncomparable to the existing state-of-the-art phrase-based systems on the task of\nEnglish-to-French translation. However, the use of large vocabulary becomes the\nbottleneck in both training and improving the performance. In this paper, we\npropose an efficient architecture to train a deep character-level neural\nmachine translation by introducing a decimator and an interpolator. The\ndecimator is used to sample the source sequence before encoding while the\ninterpolator is used to resample after decoding. Such a deep model has two\nmajor advantages. It avoids the large vocabulary issue radically; at the same\ntime, it is much faster and more memory-efficient in training than conventional\ncharacter-based models. More interestingly, our model is able to translate the\nmisspelled word like human beings.","url_abs":"http://arxiv.org/abs/1608.04738v2","url_pdf":"http://arxiv.org/pdf/1608.04738v2.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":"an-efficient-character-level-neural-machine","repo_url":"https://github.com/SwordYork/DCNMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}