@inproceedings{flachs-etal-2020-grammatical,
title = "Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses",
author = "Flachs, Simon and
Lacroix, Oph{\'e}lie and
Yannakoudakis, Helen and
Rei, Marek and
S{\o}gaard, Anders",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.680",
doi = "10.18653/v1/2020.emnlp-main.680",
pages = "8467--8478",
abstract = "Evaluation of grammatical error correction (GEC) systems has primarily focused on essays written by non-native learners of English, which however is only part of the full spectrum of GEC applications. We aim to broaden the target domain of GEC and release CWEB, a new benchmark for GEC consisting of website text generated by English speakers of varying levels of proficiency. Website data is a common and important domain that contains far fewer grammatical errors than learner essays, which we show presents a challenge to state-of-the-art GEC systems. We demonstrate that a factor behind this is the inability of systems to rely on a strong internal language model in low error density domains. We hope this work shall facilitate the development of open-domain GEC models that generalize to different topics and genres.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="flachs-etal-2020-grammatical">
<titleInfo>
<title>Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Flachs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ophélie</namePart>
<namePart type="family">Lacroix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Evaluation of grammatical error correction (GEC) systems has primarily focused on essays written by non-native learners of English, which however is only part of the full spectrum of GEC applications. We aim to broaden the target domain of GEC and release CWEB, a new benchmark for GEC consisting of website text generated by English speakers of varying levels of proficiency. Website data is a common and important domain that contains far fewer grammatical errors than learner essays, which we show presents a challenge to state-of-the-art GEC systems. We demonstrate that a factor behind this is the inability of systems to rely on a strong internal language model in low error density domains. We hope this work shall facilitate the development of open-domain GEC models that generalize to different topics and genres.</abstract>
<identifier type="citekey">flachs-etal-2020-grammatical</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.680</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.680</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8467</start>
<end>8478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses
%A Flachs, Simon
%A Lacroix, Ophélie
%A Yannakoudakis, Helen
%A Rei, Marek
%A Søgaard, Anders
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F flachs-etal-2020-grammatical
%X Evaluation of grammatical error correction (GEC) systems has primarily focused on essays written by non-native learners of English, which however is only part of the full spectrum of GEC applications. We aim to broaden the target domain of GEC and release CWEB, a new benchmark for GEC consisting of website text generated by English speakers of varying levels of proficiency. Website data is a common and important domain that contains far fewer grammatical errors than learner essays, which we show presents a challenge to state-of-the-art GEC systems. We demonstrate that a factor behind this is the inability of systems to rely on a strong internal language model in low error density domains. We hope this work shall facilitate the development of open-domain GEC models that generalize to different topics and genres.
%R 10.18653/v1/2020.emnlp-main.680
%U https://aclanthology.org/2020.emnlp-main.680
%U https://doi.org/10.18653/v1/2020.emnlp-main.680
%P 8467-8478
Markdown (Informal)
[Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses](https://aclanthology.org/2020.emnlp-main.680) (Flachs et al., EMNLP 2020)
ACL