{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1603.09727"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1603.09727\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1603.09727"},"call":"get_concepts_for_paper(arxiv_id=\"1603.09727\")"}],"by_repo":[{"repo":"freeflyxiaoma/pycorrector","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.02303"],"harvested_for_calls":[{"arxiv_id":"1812.02303","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.02303"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.02303\")"}]},{"repo":"shibing624/pycorrector","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.13922"],"harvested_for_calls":[{"arxiv_id":"2004.13922","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.13922"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.13922\")"}]},{"repo":"stanfordmlgroup/nlc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4900d4841f2eb73c7d6a1ae18c50371defd37b4100ac047e6debe50cad114c05","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}