@inproceedings{wang-zheng-2020-improving,
title = "Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples",
author = "Wang, Lihao and
Zheng, Xiaoqing",
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.228",
doi = "10.18653/v1/2020.emnlp-main.228",
pages = "2858--2869",
abstract = "A sequence-to-sequence (seq2seq) learning with neural networks empirically shows to be an effective framework for grammatical error correction (GEC), which takes a sentence with errors as input and outputs the corrected one. However, the performance of GEC models with the seq2seq framework heavily relies on the size and quality of the corpus on hand. We propose a method inspired by adversarial training to generate more meaningful and valuable training examples by continually identifying the weak spots of a model, and to enhance the model by gradually adding the generated adversarial examples to the training set. Extensive experimental results show that such adversarial training can improve both the generalization and robustness of GEC models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-zheng-2020-improving">
<titleInfo>
<title>Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lihao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Zheng</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>A sequence-to-sequence (seq2seq) learning with neural networks empirically shows to be an effective framework for grammatical error correction (GEC), which takes a sentence with errors as input and outputs the corrected one. However, the performance of GEC models with the seq2seq framework heavily relies on the size and quality of the corpus on hand. We propose a method inspired by adversarial training to generate more meaningful and valuable training examples by continually identifying the weak spots of a model, and to enhance the model by gradually adding the generated adversarial examples to the training set. Extensive experimental results show that such adversarial training can improve both the generalization and robustness of GEC models.</abstract>
<identifier type="citekey">wang-zheng-2020-improving</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.228</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.228</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2858</start>
<end>2869</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples
%A Wang, Lihao
%A Zheng, Xiaoqing
%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 wang-zheng-2020-improving
%X A sequence-to-sequence (seq2seq) learning with neural networks empirically shows to be an effective framework for grammatical error correction (GEC), which takes a sentence with errors as input and outputs the corrected one. However, the performance of GEC models with the seq2seq framework heavily relies on the size and quality of the corpus on hand. We propose a method inspired by adversarial training to generate more meaningful and valuable training examples by continually identifying the weak spots of a model, and to enhance the model by gradually adding the generated adversarial examples to the training set. Extensive experimental results show that such adversarial training can improve both the generalization and robustness of GEC models.
%R 10.18653/v1/2020.emnlp-main.228
%U https://aclanthology.org/2020.emnlp-main.228
%U https://doi.org/10.18653/v1/2020.emnlp-main.228
%P 2858-2869
Markdown (Informal)
[Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples](https://aclanthology.org/2020.emnlp-main.228) (Wang & Zheng, EMNLP 2020)
ACL