@inproceedings{hong-etal-2019-faspell,
title = "{FASP}ell: A Fast, Adaptable, Simple, Powerful {C}hinese Spell Checker Based On {DAE}-Decoder Paradigm",
author = "Hong, Yuzhong and
Yu, Xianguo and
He, Neng and
Liu, Nan and
Liu, Junhui",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5522",
doi = "10.18653/v1/D19-5522",
pages = "160--169",
abstract = "We propose a Chinese spell checker {--} FASPell based on a new paradigm which consists of a denoising autoencoder (DAE) and a decoder. In comparison with previous state-of-the-art models, the new paradigm allows our spell checker to be Faster in computation, readily Adaptable to both simplified and traditional Chinese texts produced by either humans or machines, and to require much Simpler structure to be as much Powerful in both error detection and correction. These four achievements are made possible because the new paradigm circumvents two bottlenecks. First, the DAE curtails the amount of Chinese spell checking data needed for supervised learning (to {\textless}10k sentences) by leveraging the power of unsupervisedly pre-trained masked language model as in BERT, XLNet, MASS etc. Second, the decoder helps to eliminate the use of confusion set that is deficient in flexibility and sufficiency of utilizing the salient feature of Chinese character similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2019-faspell">
<titleInfo>
<title>FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuzhong</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianguo</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neng</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a Chinese spell checker – FASPell based on a new paradigm which consists of a denoising autoencoder (DAE) and a decoder. In comparison with previous state-of-the-art models, the new paradigm allows our spell checker to be Faster in computation, readily Adaptable to both simplified and traditional Chinese texts produced by either humans or machines, and to require much Simpler structure to be as much Powerful in both error detection and correction. These four achievements are made possible because the new paradigm circumvents two bottlenecks. First, the DAE curtails the amount of Chinese spell checking data needed for supervised learning (to \textless10k sentences) by leveraging the power of unsupervisedly pre-trained masked language model as in BERT, XLNet, MASS etc. Second, the decoder helps to eliminate the use of confusion set that is deficient in flexibility and sufficiency of utilizing the salient feature of Chinese character similarity.</abstract>
<identifier type="citekey">hong-etal-2019-faspell</identifier>
<identifier type="doi">10.18653/v1/D19-5522</identifier>
<location>
<url>https://aclanthology.org/D19-5522</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>160</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm
%A Hong, Yuzhong
%A Yu, Xianguo
%A He, Neng
%A Liu, Nan
%A Liu, Junhui
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F hong-etal-2019-faspell
%X We propose a Chinese spell checker – FASPell based on a new paradigm which consists of a denoising autoencoder (DAE) and a decoder. In comparison with previous state-of-the-art models, the new paradigm allows our spell checker to be Faster in computation, readily Adaptable to both simplified and traditional Chinese texts produced by either humans or machines, and to require much Simpler structure to be as much Powerful in both error detection and correction. These four achievements are made possible because the new paradigm circumvents two bottlenecks. First, the DAE curtails the amount of Chinese spell checking data needed for supervised learning (to \textless10k sentences) by leveraging the power of unsupervisedly pre-trained masked language model as in BERT, XLNet, MASS etc. Second, the decoder helps to eliminate the use of confusion set that is deficient in flexibility and sufficiency of utilizing the salient feature of Chinese character similarity.
%R 10.18653/v1/D19-5522
%U https://aclanthology.org/D19-5522
%U https://doi.org/10.18653/v1/D19-5522
%P 160-169
Markdown (Informal)
[FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm](https://aclanthology.org/D19-5522) (Hong et al., WNUT 2019)
ACL
- Yuzhong Hong, Xianguo Yu, Neng He, Nan Liu, and Junhui Liu. 2019. FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), pages 160–169, Hong Kong, China. Association for Computational Linguistics.