@inproceedings{fivez-etal-2017-unsupervised,
title = "Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings",
author = "Fivez, Pieter and
{\v{S}}uster, Simon and
Daelemans, Walter",
editor = "Cohen, Kevin Bretonnel and
Demner-Fushman, Dina and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2017",
month = aug,
year = "2017",
address = "Vancouver, Canada,",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2317",
doi = "10.18653/v1/W17-2317",
pages = "143--148",
abstract = "We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. We greatly outperform two baseline off-the-shelf spelling correction tools on a manually annotated MIMIC-III test set, and counter the frequency bias of an optimized noisy channel model, showing that neural embeddings can be successfully exploited to include context-awareness in a spelling correction model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fivez-etal-2017-unsupervised">
<titleInfo>
<title>Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pieter</namePart>
<namePart type="family">Fivez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Šuster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada,</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. We greatly outperform two baseline off-the-shelf spelling correction tools on a manually annotated MIMIC-III test set, and counter the frequency bias of an optimized noisy channel model, showing that neural embeddings can be successfully exploited to include context-awareness in a spelling correction model.</abstract>
<identifier type="citekey">fivez-etal-2017-unsupervised</identifier>
<identifier type="doi">10.18653/v1/W17-2317</identifier>
<location>
<url>https://aclanthology.org/W17-2317</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>143</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings
%A Fivez, Pieter
%A Šuster, Simon
%A Daelemans, Walter
%Y Cohen, Kevin Bretonnel
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S BioNLP 2017
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada,
%F fivez-etal-2017-unsupervised
%X We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. We greatly outperform two baseline off-the-shelf spelling correction tools on a manually annotated MIMIC-III test set, and counter the frequency bias of an optimized noisy channel model, showing that neural embeddings can be successfully exploited to include context-awareness in a spelling correction model.
%R 10.18653/v1/W17-2317
%U https://aclanthology.org/W17-2317
%U https://doi.org/10.18653/v1/W17-2317
%P 143-148
Markdown (Informal)
[Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings](https://aclanthology.org/W17-2317) (Fivez et al., BioNLP 2017)
ACL