@inproceedings{liu-etal-2021-plome,
title = "{PLOME}: Pre-training with Misspelled Knowledge for {C}hinese Spelling Correction",
author = "Liu, Shulin and
Yang, Tao and
Yue, Tianchi and
Zhang, Feng and
Wang, Di",
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 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.233",
doi = "10.18653/v1/2021.acl-long.233",
pages = "2991--3000",
abstract = "Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors. To this end, PLOME masks the chosen tokens with similar characters according to a confusion set rather than the fixed token {``}[MASK]{''} as in BERT. Besides character prediction, PLOME also introduces pronunciation prediction to learn the misspelled knowledge on phonic level. Moreover, phonological and visual similarity knowledge is important to this task. PLOME utilizes GRU networks to model such knowledge based on characters{'} phonics and strokes. Experiments are conducted on widely used benchmarks. Our method achieves superior performance against state-of-the-art approaches by a remarkable margin. We release the source code and pre-trained model for further use by the community (\url{https://github.com/liushulinle/PLOME}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-plome">
<titleInfo>
<title>PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shulin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianchi</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wang</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 1: Long 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>Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors. To this end, PLOME masks the chosen tokens with similar characters according to a confusion set rather than the fixed token “[MASK]” as in BERT. Besides character prediction, PLOME also introduces pronunciation prediction to learn the misspelled knowledge on phonic level. Moreover, phonological and visual similarity knowledge is important to this task. PLOME utilizes GRU networks to model such knowledge based on characters’ phonics and strokes. Experiments are conducted on widely used benchmarks. Our method achieves superior performance against state-of-the-art approaches by a remarkable margin. We release the source code and pre-trained model for further use by the community (https://github.com/liushulinle/PLOME).</abstract>
<identifier type="citekey">liu-etal-2021-plome</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.233</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.233</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2991</start>
<end>3000</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction
%A Liu, Shulin
%A Yang, Tao
%A Yue, Tianchi
%A Zhang, Feng
%A Wang, Di
%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 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-plome
%X Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for CSC, which jointly learns how to understand language and correct spelling errors. To this end, PLOME masks the chosen tokens with similar characters according to a confusion set rather than the fixed token “[MASK]” as in BERT. Besides character prediction, PLOME also introduces pronunciation prediction to learn the misspelled knowledge on phonic level. Moreover, phonological and visual similarity knowledge is important to this task. PLOME utilizes GRU networks to model such knowledge based on characters’ phonics and strokes. Experiments are conducted on widely used benchmarks. Our method achieves superior performance against state-of-the-art approaches by a remarkable margin. We release the source code and pre-trained model for further use by the community (https://github.com/liushulinle/PLOME).
%R 10.18653/v1/2021.acl-long.233
%U https://aclanthology.org/2021.acl-long.233
%U https://doi.org/10.18653/v1/2021.acl-long.233
%P 2991-3000
Markdown (Informal)
[PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction](https://aclanthology.org/2021.acl-long.233) (Liu et al., ACL-IJCNLP 2021)
ACL
- Shulin Liu, Tao Yang, Tianchi Yue, Feng Zhang, and Di Wang. 2021. PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2991–3000, Online. Association for Computational Linguistics.