{"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/unsupervised-context-sensitive-spelling-1","title":"Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings","arxiv_id":"1710.07045","date":"2017-10-19","proceeding":null,"authors":["Pieter Fivez","Simon Šuster","Walter Daelemans"],"abstract":"We present an unsupervised context-sensitive spelling correction method for\nclinical free-text that uses word and character n-gram embeddings. Our method\ngenerates misspelling replacement candidates and ranks them according to their\nsemantic fit, by calculating a weighted cosine similarity between the\nvectorized representation of a candidate and the misspelling context. To tune\nthe parameters of this model, we generate self-induced spelling error corpora.\nWe perform our experiments for two languages. For English, we greatly\noutperform off-the-shelf spelling correction tools on a manually annotated\nMIMIC-III test set, and counter the frequency bias of a noisy channel model,\nshowing that neural embeddings can be successfully exploited to improve upon\nthe state-of-the-art. For Dutch, we also outperform an off-the-shelf spelling\ncorrection tool on manually annotated clinical records from the Antwerp\nUniversity Hospital, but can offer no empirical evidence that our method\ncounters the frequency bias of a noisy channel model in this case as well.\nHowever, both our context-sensitive model and our implementation of the noisy\nchannel model obtain high scores on the test set, establishing a\nstate-of-the-art for Dutch clinical spelling correction with the noisy channel\nmodel.","url_abs":"http://arxiv.org/abs/1710.07045v1","url_pdf":"http://arxiv.org/pdf/1710.07045v1.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":"unsupervised-context-sensitive-spelling-1","repo_url":"https://github.com/clips/clinspell","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"spelling-correction","task_name":"Spelling Correction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}