@inproceedings{choshen-abend-2018-automatic,
title = "Automatic Metric Validation for Grammatical Error Correction",
author = "Choshen, Leshem and
Abend, Omri",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1127",
doi = "10.18653/v1/P18-1127",
pages = "1372--1382",
abstract = "Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties in the existing methodology. Experiments with MAEGE shed a new light on metric quality, showing for example that the standard $M^2$ metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analysis of metric behavior, showing that some types of valid edits are consistently penalized by existing metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choshen-abend-2018-automatic">
<titleInfo>
<title>Automatic Metric Validation for Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties in the existing methodology. Experiments with MAEGE shed a new light on metric quality, showing for example that the standard M² metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analysis of metric behavior, showing that some types of valid edits are consistently penalized by existing metrics.</abstract>
<identifier type="citekey">choshen-abend-2018-automatic</identifier>
<identifier type="doi">10.18653/v1/P18-1127</identifier>
<location>
<url>https://aclanthology.org/P18-1127</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>1372</start>
<end>1382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Metric Validation for Grammatical Error Correction
%A Choshen, Leshem
%A Abend, Omri
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F choshen-abend-2018-automatic
%X Metric validation in Grammatical Error Correction (GEC) is currently done by observing the correlation between human and metric-induced rankings. However, such correlation studies are costly, methodologically troublesome, and suffer from low inter-rater agreement. We propose MAEGE, an automatic methodology for GEC metric validation, that overcomes many of the difficulties in the existing methodology. Experiments with MAEGE shed a new light on metric quality, showing for example that the standard M² metric fares poorly on corpus-level ranking. Moreover, we use MAEGE to perform a detailed analysis of metric behavior, showing that some types of valid edits are consistently penalized by existing metrics.
%R 10.18653/v1/P18-1127
%U https://aclanthology.org/P18-1127
%U https://doi.org/10.18653/v1/P18-1127
%P 1372-1382
Markdown (Informal)
[Automatic Metric Validation for Grammatical Error Correction](https://aclanthology.org/P18-1127) (Choshen & Abend, ACL 2018)
ACL