@inproceedings{jayanthi-etal-2020-neuspell,
title = "{N}eu{S}pell: A Neural Spelling Correction Toolkit",
author = "Jayanthi, Sai Muralidhar and
Pruthi, Danish and
Neubig, Graham",
editor = "Liu, Qun and
Schlangen, David",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-demos.21",
doi = "10.18653/v1/2020.emnlp-demos.21",
pages = "158--164",
abstract = "We introduce NeuSpell, an open-source toolkit for spelling correction in English. Our toolkit comprises ten different models, and benchmarks them on naturally occurring misspellings from multiple sources. We find that many systems do not adequately leverage the context around the misspelt token. To remedy this, (i) we train neural models using spelling errors in context, synthetically constructed by reverse engineering isolated misspellings; and (ii) use richer representations of the context. By training on our synthetic examples, correction rates improve by 9{\%} (absolute) compared to the case when models are trained on randomly sampled character perturbations. Using richer contextual representations boosts the correction rate by another 3{\%}. Our toolkit enables practitioners to use our proposed and existing spelling correction systems, both via a simple unified command line, as well as a web interface. Among many potential applications, we demonstrate the utility of our spell-checkers in combating adversarial misspellings. The toolkit can be accessed at neuspell.github.io.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jayanthi-etal-2020-neuspell">
<titleInfo>
<title>NeuSpell: A Neural Spelling Correction Toolkit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Muralidhar</namePart>
<namePart type="family">Jayanthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danish</namePart>
<namePart type="family">Pruthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce NeuSpell, an open-source toolkit for spelling correction in English. Our toolkit comprises ten different models, and benchmarks them on naturally occurring misspellings from multiple sources. We find that many systems do not adequately leverage the context around the misspelt token. To remedy this, (i) we train neural models using spelling errors in context, synthetically constructed by reverse engineering isolated misspellings; and (ii) use richer representations of the context. By training on our synthetic examples, correction rates improve by 9% (absolute) compared to the case when models are trained on randomly sampled character perturbations. Using richer contextual representations boosts the correction rate by another 3%. Our toolkit enables practitioners to use our proposed and existing spelling correction systems, both via a simple unified command line, as well as a web interface. Among many potential applications, we demonstrate the utility of our spell-checkers in combating adversarial misspellings. The toolkit can be accessed at neuspell.github.io.</abstract>
<identifier type="citekey">jayanthi-etal-2020-neuspell</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-demos.21</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-demos.21</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>158</start>
<end>164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NeuSpell: A Neural Spelling Correction Toolkit
%A Jayanthi, Sai Muralidhar
%A Pruthi, Danish
%A Neubig, Graham
%Y Liu, Qun
%Y Schlangen, David
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2020
%8 October
%I Association for Computational Linguistics
%C Online
%F jayanthi-etal-2020-neuspell
%X We introduce NeuSpell, an open-source toolkit for spelling correction in English. Our toolkit comprises ten different models, and benchmarks them on naturally occurring misspellings from multiple sources. We find that many systems do not adequately leverage the context around the misspelt token. To remedy this, (i) we train neural models using spelling errors in context, synthetically constructed by reverse engineering isolated misspellings; and (ii) use richer representations of the context. By training on our synthetic examples, correction rates improve by 9% (absolute) compared to the case when models are trained on randomly sampled character perturbations. Using richer contextual representations boosts the correction rate by another 3%. Our toolkit enables practitioners to use our proposed and existing spelling correction systems, both via a simple unified command line, as well as a web interface. Among many potential applications, we demonstrate the utility of our spell-checkers in combating adversarial misspellings. The toolkit can be accessed at neuspell.github.io.
%R 10.18653/v1/2020.emnlp-demos.21
%U https://aclanthology.org/2020.emnlp-demos.21
%U https://doi.org/10.18653/v1/2020.emnlp-demos.21
%P 158-164
Markdown (Informal)
[NeuSpell: A Neural Spelling Correction Toolkit](https://aclanthology.org/2020.emnlp-demos.21) (Jayanthi et al., EMNLP 2020)
ACL
- Sai Muralidhar Jayanthi, Danish Pruthi, and Graham Neubig. 2020. NeuSpell: A Neural Spelling Correction Toolkit. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 158–164, Online. Association for Computational Linguistics.