@inproceedings{flachs-etal-2019-simple,
title = "A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors",
author = "Flachs, Simon and
Lacroix, Oph{\'e}lie and
Rei, Marek and
Yannakoudakis, Helen and
S{\o}gaard, Anders",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1251/",
doi = "10.18653/v1/N19-1251",
pages = "2418--2427",
abstract = "While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data. We observe that rule-based error generation is less sensitive to syntactic parsing errors and irregularities than error detection and explore a simple, yet efficient approach to getting the best of both worlds: We train neural sequential labelers on the combination of large volumes of silver standard data, obtained through rule-based error generation, and gold standard data. We show that our simple protocol leads to more robust detection of SVA errors on both in-domain and out-of-domain data, as well as in the context of other errors and long-distance dependencies; and across four standard benchmarks, the induced model on average achieves a new state of the art."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="flachs-etal-2019-simple">
<titleInfo>
<title>A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors</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">Marek</namePart>
<namePart type="family">Rei</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">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data. We observe that rule-based error generation is less sensitive to syntactic parsing errors and irregularities than error detection and explore a simple, yet efficient approach to getting the best of both worlds: We train neural sequential labelers on the combination of large volumes of silver standard data, obtained through rule-based error generation, and gold standard data. We show that our simple protocol leads to more robust detection of SVA errors on both in-domain and out-of-domain data, as well as in the context of other errors and long-distance dependencies; and across four standard benchmarks, the induced model on average achieves a new state of the art.</abstract>
<identifier type="citekey">flachs-etal-2019-simple</identifier>
<identifier type="doi">10.18653/v1/N19-1251</identifier>
<location>
<url>https://aclanthology.org/N19-1251/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2418</start>
<end>2427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors
%A Flachs, Simon
%A Lacroix, Ophélie
%A Rei, Marek
%A Yannakoudakis, Helen
%A Søgaard, Anders
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F flachs-etal-2019-simple
%X While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data. We observe that rule-based error generation is less sensitive to syntactic parsing errors and irregularities than error detection and explore a simple, yet efficient approach to getting the best of both worlds: We train neural sequential labelers on the combination of large volumes of silver standard data, obtained through rule-based error generation, and gold standard data. We show that our simple protocol leads to more robust detection of SVA errors on both in-domain and out-of-domain data, as well as in the context of other errors and long-distance dependencies; and across four standard benchmarks, the induced model on average achieves a new state of the art.
%R 10.18653/v1/N19-1251
%U https://aclanthology.org/N19-1251/
%U https://doi.org/10.18653/v1/N19-1251
%P 2418-2427
Markdown (Informal)
[A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors](https://aclanthology.org/N19-1251/) (Flachs et al., NAACL 2019)
- A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors (Flachs et al., NAACL 2019)
ACL
- Simon Flachs, Ophélie Lacroix, Marek Rei, Helen Yannakoudakis, and Anders Søgaard. 2019. A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2418–2427, Minneapolis, Minnesota. Association for Computational Linguistics.