@inproceedings{ji-etal-2021-spellbert,
title = "{S}pell{BERT}: A Lightweight Pretrained Model for {C}hinese Spelling Check",
author = "Ji, Tuo and
Yan, Hang and
Qiu, Xipeng",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.287",
doi = "10.18653/v1/2021.emnlp-main.287",
pages = "3544--3551",
abstract = "Chinese Spelling Check (CSC) is to detect and correct Chinese spelling errors. Many models utilize a predefined confusion set to learn a mapping between correct characters and its visually similar or phonetically similar misuses but the mapping may be out-of-domain. To that end, we propose SpellBERT, a pretrained model with graph-based extra features and independent on confusion set. To explicitly capture the two erroneous patterns, we employ a graph neural network to introduce radical and pinyin information as visual and phonetic features. For better fusing these features with character representations, we devise masked language model alike pre-training tasks. With this feature-rich pre-training, SpellBERT with only half size of BERT can show competitive performance and make a state-of-the-art result on the OCR dataset where most of the errors are not covered by the existing confusion set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ji-etal-2021-spellbert">
<titleInfo>
<title>SpellBERT: A Lightweight Pretrained Model for Chinese Spelling Check</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuo</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese Spelling Check (CSC) is to detect and correct Chinese spelling errors. Many models utilize a predefined confusion set to learn a mapping between correct characters and its visually similar or phonetically similar misuses but the mapping may be out-of-domain. To that end, we propose SpellBERT, a pretrained model with graph-based extra features and independent on confusion set. To explicitly capture the two erroneous patterns, we employ a graph neural network to introduce radical and pinyin information as visual and phonetic features. For better fusing these features with character representations, we devise masked language model alike pre-training tasks. With this feature-rich pre-training, SpellBERT with only half size of BERT can show competitive performance and make a state-of-the-art result on the OCR dataset where most of the errors are not covered by the existing confusion set.</abstract>
<identifier type="citekey">ji-etal-2021-spellbert</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.287</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.287</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3544</start>
<end>3551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpellBERT: A Lightweight Pretrained Model for Chinese Spelling Check
%A Ji, Tuo
%A Yan, Hang
%A Qiu, Xipeng
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F ji-etal-2021-spellbert
%X Chinese Spelling Check (CSC) is to detect and correct Chinese spelling errors. Many models utilize a predefined confusion set to learn a mapping between correct characters and its visually similar or phonetically similar misuses but the mapping may be out-of-domain. To that end, we propose SpellBERT, a pretrained model with graph-based extra features and independent on confusion set. To explicitly capture the two erroneous patterns, we employ a graph neural network to introduce radical and pinyin information as visual and phonetic features. For better fusing these features with character representations, we devise masked language model alike pre-training tasks. With this feature-rich pre-training, SpellBERT with only half size of BERT can show competitive performance and make a state-of-the-art result on the OCR dataset where most of the errors are not covered by the existing confusion set.
%R 10.18653/v1/2021.emnlp-main.287
%U https://aclanthology.org/2021.emnlp-main.287
%U https://doi.org/10.18653/v1/2021.emnlp-main.287
%P 3544-3551
Markdown (Informal)
[SpellBERT: A Lightweight Pretrained Model for Chinese Spelling Check](https://aclanthology.org/2021.emnlp-main.287) (Ji et al., EMNLP 2021)
ACL