{"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/debugging-neural-machine-translations","title":"Debugging Neural Machine Translations","arxiv_id":"1808.02733","date":"2018-08-08","proceeding":null,"authors":["Matīss Rikters"],"abstract":"In this paper, we describe a tool for debugging the output and attention\nweights of neural machine translation (NMT) systems and for improved\nestimations of confidence about the output based on the attention. The purpose\nof the tool is to help researchers and developers find weak and faulty example\ntranslations that their NMT systems produce without the need for reference\ntranslations. Our tool also includes an option to directly compare translation\noutputs from two different NMT engines or experiments. In addition, we present\na demo website of our tool with examples of good and bad translations:\nhttp://attention.lielakeda.lv","url_abs":"http://arxiv.org/abs/1808.02733v1","url_pdf":"http://arxiv.org/pdf/1808.02733v1.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":"debugging-neural-machine-translations","repo_url":"https://github.com/M4t1ss/SoftAlignments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","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-wmt-2017-latvian","task":"Machine Translation","dataset":"WMT 2017 Latvian-English","model":"RNN","rank_in_archive_order":4,"of":4,"metrics":{"BLEU":"-"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}