{"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-language-correction-with-character","title":"Neural Language Correction with Character-Based Attention","arxiv_id":"1603.09727","date":"2016-03-31","proceeding":null,"authors":["Ziang Xie","Anand Avati","Naveen Arivazhagan","Dan Jurafsky","Andrew Y. Ng"],"abstract":"Natural language correction has the potential to help language learners\nimprove their writing skills. While approaches with separate classifiers for\ndifferent error types have high precision, they do not flexibly handle errors\nsuch as redundancy or non-idiomatic phrasing. On the other hand, word and\nphrase-based machine translation methods are not designed to cope with\northographic errors, and have recently been outpaced by neural models.\nMotivated by these issues, we present a neural network-based approach to\nlanguage correction. The core component of our method is an encoder-decoder\nrecurrent neural network with an attention mechanism. By operating at the\ncharacter level, the network avoids the problem of out-of-vocabulary words. We\nillustrate the flexibility of our approach on dataset of noisy, user-generated\ntext collected from an English learner forum. When combined with a language\nmodel, our method achieves a state-of-the-art $F_{0.5}$-score on the CoNLL 2014\nShared Task. We further demonstrate that training the network on additional\ndata with synthesized errors can improve performance.","url_abs":"http://arxiv.org/abs/1603.09727v1","url_pdf":"http://arxiv.org/pdf/1603.09727v1.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-language-correction-with-character","repo_url":"https://github.com/freeflyxiaoma/pycorrector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"neural-language-correction-with-character","repo_url":"https://github.com/shibing624/pycorrector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"neural-language-correction-with-character","repo_url":"https://github.com/stanfordmlgroup/nlc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1603.09727","atlas_url":"https://app.syntology.ai/?focus=1603.09727","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}