@article{napoles-etal-2019-enabling,
title = "Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses",
author = "Napoles, Courtney and
N{\u{a}}dejde, Maria and
Tetreault, Joel",
editor = "Lee, Lillian and
Johnson, Mark and
Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "7",
year = "2019",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q19-1032",
doi = "10.1162/tacl_a_00282",
pages = "551--566",
abstract = "Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data set and metric. We present a multiple-reference test corpus for GEC that includes 4,000 sentences in two new domains (formal and informal writing by native English speakers) and 2,000 sentences from a diverse set of non-native student writing. We also collect human judgments of several GEC systems on this new test set and perform a meta-evaluation, assessing how reliable automatic metrics are across these domains. We find that commonly used GEC metrics have inconsistent performance across domains, and therefore we propose a new ensemble metric that is robust on all three domains of text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="napoles-etal-2019-enabling">
<titleInfo>
<title>Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Nădejde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data set and metric. We present a multiple-reference test corpus for GEC that includes 4,000 sentences in two new domains (formal and informal writing by native English speakers) and 2,000 sentences from a diverse set of non-native student writing. We also collect human judgments of several GEC systems on this new test set and perform a meta-evaluation, assessing how reliable automatic metrics are across these domains. We find that commonly used GEC metrics have inconsistent performance across domains, and therefore we propose a new ensemble metric that is robust on all three domains of text.</abstract>
<identifier type="citekey">napoles-etal-2019-enabling</identifier>
<identifier type="doi">10.1162/tacl_a_00282</identifier>
<location>
<url>https://aclanthology.org/Q19-1032</url>
</location>
<part>
<date>2019</date>
<detail type="volume"><number>7</number></detail>
<extent unit="page">
<start>551</start>
<end>566</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses
%A Napoles, Courtney
%A Nădejde, Maria
%A Tetreault, Joel
%J Transactions of the Association for Computational Linguistics
%D 2019
%V 7
%I MIT Press
%C Cambridge, MA
%F napoles-etal-2019-enabling
%X Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data set and metric. We present a multiple-reference test corpus for GEC that includes 4,000 sentences in two new domains (formal and informal writing by native English speakers) and 2,000 sentences from a diverse set of non-native student writing. We also collect human judgments of several GEC systems on this new test set and perform a meta-evaluation, assessing how reliable automatic metrics are across these domains. We find that commonly used GEC metrics have inconsistent performance across domains, and therefore we propose a new ensemble metric that is robust on all three domains of text.
%R 10.1162/tacl_a_00282
%U https://aclanthology.org/Q19-1032
%U https://doi.org/10.1162/tacl_a_00282
%P 551-566
Markdown (Informal)
[Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses](https://aclanthology.org/Q19-1032) (Napoles et al., TACL 2019)
ACL