{"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/neural-machine-translation-with-characters","title":"Neural Machine Translation with Characters and Hierarchical Encoding","arxiv_id":"1610.06550","date":"2016-10-20","proceeding":null,"authors":["Alexander Rosenberg Johansen","Jonas Meinertz Hansen","Elias Khazen Obeid","Casper Kaae Sønderby","Ole Winther"],"abstract":"Most existing Neural Machine Translation models use groups of characters or\nwhole words as their unit of input and output. We propose a model with a\nhierarchical char2word encoder, that takes individual characters both as input\nand output. We first argue that this hierarchical representation of the\ncharacter encoder reduces computational complexity, and show that it improves\ntranslation performance. Secondly, by qualitatively studying attention plots\nfrom the decoder we find that the model learns to compress common words into a\nsingle embedding whereas rare words, such as names and places, are represented\ncharacter by character.","url_abs":"http://arxiv.org/abs/1610.06550v1","url_pdf":"http://arxiv.org/pdf/1610.06550v1.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":"neural-machine-translation-with-characters","repo_url":"https://github.com/Styrke/master-code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"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}