@inproceedings{li-etal-2021-exploration,
title = "Exploration and Exploitation: Two Ways to Improve {C}hinese Spelling Correction Models",
author = "Li, Chong and
Zhang, Cenyuan and
Zheng, Xiaoqing and
Huang, Xuanjing",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.56",
doi = "10.18653/v1/2021.acl-short.56",
pages = "441--446",
abstract = "A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one. However, CSC models may fail to correct spelling errors covered by the confusion sets, and also will encounter unseen ones. We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances, and apply a task-specific pre-training strategy to enhance the model. The generated adversarial examples are gradually added to the training set. Experimental results show that such an adversarial training method combined with the pre-training strategy can improve both the generalization and robustness of multiple CSC models across three different datasets, achieving state-of-the-art performance for CSC task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-exploration">
<titleInfo>
<title>Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cenyuan</namePart>
<namePart type="family">Zhang</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>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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 learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one. However, CSC models may fail to correct spelling errors covered by the confusion sets, and also will encounter unseen ones. We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances, and apply a task-specific pre-training strategy to enhance the model. The generated adversarial examples are gradually added to the training set. Experimental results show that such an adversarial training method combined with the pre-training strategy can improve both the generalization and robustness of multiple CSC models across three different datasets, achieving state-of-the-art performance for CSC task.</abstract>
<identifier type="citekey">li-etal-2021-exploration</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.56</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.56</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>441</start>
<end>446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
%A Li, Chong
%A Zhang, Cenyuan
%A Zheng, Xiaoqing
%A Huang, Xuanjing
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F li-etal-2021-exploration
%X A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one. However, CSC models may fail to correct spelling errors covered by the confusion sets, and also will encounter unseen ones. We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances, and apply a task-specific pre-training strategy to enhance the model. The generated adversarial examples are gradually added to the training set. Experimental results show that such an adversarial training method combined with the pre-training strategy can improve both the generalization and robustness of multiple CSC models across three different datasets, achieving state-of-the-art performance for CSC task.
%R 10.18653/v1/2021.acl-short.56
%U https://aclanthology.org/2021.acl-short.56
%U https://doi.org/10.18653/v1/2021.acl-short.56
%P 441-446
Markdown (Informal)
[Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models](https://aclanthology.org/2021.acl-short.56) (Li et al., ACL-IJCNLP 2021)
ACL