@inproceedings{asano-etal-2017-reference,
title = "Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems",
author = "Asano, Hiroki and
Mizumoto, Tomoya and
Inui, Kentaro",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-2058",
pages = "343--348",
abstract = "In grammatical error correction (GEC), automatically evaluating system outputs requires gold-standard references, which must be created manually and thus tend to be both expensive and limited in coverage. To address this problem, a reference-less approach has recently emerged; however, previous reference-less metrics that only consider the criterion of grammaticality, have not worked as well as reference-based metrics. This study explores the potential of extending a prior grammaticality-based method to establish a reference-less evaluation method for GEC systems. Further, we empirically show that a reference-less metric that combines fluency and meaning preservation with grammaticality provides a better estimate of manual scores than that of commonly used reference-based metrics. To our knowledge, this is the first study that provides empirical evidence that a reference-less metric can replace reference-based metrics in evaluating GEC systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asano-etal-2017-reference">
<titleInfo>
<title>Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Asano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoya</namePart>
<namePart type="family">Mizumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In grammatical error correction (GEC), automatically evaluating system outputs requires gold-standard references, which must be created manually and thus tend to be both expensive and limited in coverage. To address this problem, a reference-less approach has recently emerged; however, previous reference-less metrics that only consider the criterion of grammaticality, have not worked as well as reference-based metrics. This study explores the potential of extending a prior grammaticality-based method to establish a reference-less evaluation method for GEC systems. Further, we empirically show that a reference-less metric that combines fluency and meaning preservation with grammaticality provides a better estimate of manual scores than that of commonly used reference-based metrics. To our knowledge, this is the first study that provides empirical evidence that a reference-less metric can replace reference-based metrics in evaluating GEC systems.</abstract>
<identifier type="citekey">asano-etal-2017-reference</identifier>
<location>
<url>https://aclanthology.org/I17-2058</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>343</start>
<end>348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems
%A Asano, Hiroki
%A Mizumoto, Tomoya
%A Inui, Kentaro
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F asano-etal-2017-reference
%X In grammatical error correction (GEC), automatically evaluating system outputs requires gold-standard references, which must be created manually and thus tend to be both expensive and limited in coverage. To address this problem, a reference-less approach has recently emerged; however, previous reference-less metrics that only consider the criterion of grammaticality, have not worked as well as reference-based metrics. This study explores the potential of extending a prior grammaticality-based method to establish a reference-less evaluation method for GEC systems. Further, we empirically show that a reference-less metric that combines fluency and meaning preservation with grammaticality provides a better estimate of manual scores than that of commonly used reference-based metrics. To our knowledge, this is the first study that provides empirical evidence that a reference-less metric can replace reference-based metrics in evaluating GEC systems.
%U https://aclanthology.org/I17-2058
%P 343-348
Markdown (Informal)
[Reference-based Metrics can be Replaced with Reference-less Metrics in Evaluating Grammatical Error Correction Systems](https://aclanthology.org/I17-2058) (Asano et al., IJCNLP 2017)
ACL