{"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-of-text-from-non","title":"Neural Machine Translation of Text from Non-Native Speakers","arxiv_id":"1808.06267","date":"2018-08-19","proceeding":"NAACL 2019 6","authors":["Antonios Anastasopoulos","Alison Lui","Toan Nguyen","David Chiang"],"abstract":"Neural Machine Translation (NMT) systems are known to degrade when confronted\nwith noisy data, especially when the system is trained only on clean data. In\nthis paper, we show that augmenting training data with sentences containing\nartificially-introduced grammatical errors can make the system more robust to\nsuch errors. In combination with an automatic grammar error correction system,\nwe can recover 1.5 BLEU out of 2.4 BLEU lost due to grammatical errors. We also\npresent a set of Spanish translations of the JFLEG grammar error correction\ncorpus, which allows for testing NMT robustness to real grammatical errors.","url_abs":"http://arxiv.org/abs/1808.06267v2","url_pdf":"http://arxiv.org/pdf/1808.06267v2.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-of-text-from-non","repo_url":"https://bitbucket.org/antonis/nmt-grammar-noise","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"neural-machine-translation-of-text-from-non","repo_url":"https://github.com/tnq177/nmt_text_from_non_native_speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.06267","atlas_url":"https://app.syntology.ai/?focus=1808.06267","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}