@inproceedings{flor-etal-2019-benchmark,
title = "A Benchmark Corpus of {E}nglish Misspellings and a Minimally-supervised Model for Spelling Correction",
author = "Flor, Michael and
Fried, Michael and
Rozovskaya, Alla",
editor = "Yannakoudakis, Helen and
Kochmar, Ekaterina and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Zesch, Torsten",
booktitle = "Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4407",
doi = "10.18653/v1/W19-4407",
pages = "76--86",
abstract = "Spelling correction has attracted a lot of attention in the NLP community. However, models have been usually evaluated on artificiallycreated or proprietary corpora. A publiclyavailable corpus of authentic misspellings, annotated in context, is still lacking. To address this, we present and release an annotated data set of 6,121 spelling errors in context, based on a corpus of essays written by English language learners. We also develop a minimallysupervised context-aware approach to spelling correction. It achieves strong results on our data: 88.12{\%} accuracy. This approach can also train with a minimal amount of annotated data (performance reduced by less than 1{\%}). Furthermore, this approach allows easy portability to new domains. We evaluate our model on data from a medical domain and demonstrate that it rivals the performance of a model trained and tuned on in-domain data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="flor-etal-2019-benchmark">
<titleInfo>
<title>A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Flor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Fried</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alla</namePart>
<namePart type="family">Rozovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spelling correction has attracted a lot of attention in the NLP community. However, models have been usually evaluated on artificiallycreated or proprietary corpora. A publiclyavailable corpus of authentic misspellings, annotated in context, is still lacking. To address this, we present and release an annotated data set of 6,121 spelling errors in context, based on a corpus of essays written by English language learners. We also develop a minimallysupervised context-aware approach to spelling correction. It achieves strong results on our data: 88.12% accuracy. This approach can also train with a minimal amount of annotated data (performance reduced by less than 1%). Furthermore, this approach allows easy portability to new domains. We evaluate our model on data from a medical domain and demonstrate that it rivals the performance of a model trained and tuned on in-domain data.</abstract>
<identifier type="citekey">flor-etal-2019-benchmark</identifier>
<identifier type="doi">10.18653/v1/W19-4407</identifier>
<location>
<url>https://aclanthology.org/W19-4407</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>76</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction
%A Flor, Michael
%A Fried, Michael
%A Rozovskaya, Alla
%Y Yannakoudakis, Helen
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Zesch, Torsten
%S Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F flor-etal-2019-benchmark
%X Spelling correction has attracted a lot of attention in the NLP community. However, models have been usually evaluated on artificiallycreated or proprietary corpora. A publiclyavailable corpus of authentic misspellings, annotated in context, is still lacking. To address this, we present and release an annotated data set of 6,121 spelling errors in context, based on a corpus of essays written by English language learners. We also develop a minimallysupervised context-aware approach to spelling correction. It achieves strong results on our data: 88.12% accuracy. This approach can also train with a minimal amount of annotated data (performance reduced by less than 1%). Furthermore, this approach allows easy portability to new domains. We evaluate our model on data from a medical domain and demonstrate that it rivals the performance of a model trained and tuned on in-domain data.
%R 10.18653/v1/W19-4407
%U https://aclanthology.org/W19-4407
%U https://doi.org/10.18653/v1/W19-4407
%P 76-86
Markdown (Informal)
[A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction](https://aclanthology.org/W19-4407) (Flor et al., BEA 2019)
ACL