@inproceedings{he-etal-2023-umrspell,
title = "{UMRS}pell: Unifying the Detection and Correction Parts of Pre-trained Models towards {C}hinese Missing, Redundant, and Spelling Correction",
author = "He, Zheyu and
Zhu, Yujin and
Wang, Linlin and
Xu, Liang",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.570",
doi = "10.18653/v1/2023.acl-long.570",
pages = "10238--10250",
abstract = "Chinese Spelling Correction (CSC) is the task of detecting and correcting misspelled charac- ters in Chinese texts. As an important step for various downstream tasks, CSC confronts two challenges: 1) Character-level errors consist not only of spelling errors but also of missing and redundant ones that cause variable length between input and output texts, for which most CSC methods could not handle well because of the consistence length of texts required by their inherent detection-correction framework. Con- sequently, the two errors are considered out- side the scope and left to future work, despite the fact that they are widely found and bound to CSC task in Chinese industrial scenario, such as Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR). 2) Most existing CSC methods focus on either detector or corrector and train different mod- els for each one, respectively, leading to in- sufficiency of parameters sharing. To address these issues, we propose a novel model UMR- Spell to learn detection and correction parts together at the same time from a multi-task learning perspective by using a detection trans- mission self-attention matrix, and flexibly deal with both missing, redundant, and spelling er- rors through re-tagging rules. Furthermore, we build a new dataset ECMR-2023 containing five kinds of character-level errors to enrich the CSC task closer to real-world applications. Ex- periments on both SIGHAN benchmarks and ECMR-2023 demonstrate the significant effec- tiveness of UMRSpell over previous represen- tative baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2023-umrspell">
<titleInfo>
<title>UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheyu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese Spelling Correction (CSC) is the task of detecting and correcting misspelled charac- ters in Chinese texts. As an important step for various downstream tasks, CSC confronts two challenges: 1) Character-level errors consist not only of spelling errors but also of missing and redundant ones that cause variable length between input and output texts, for which most CSC methods could not handle well because of the consistence length of texts required by their inherent detection-correction framework. Con- sequently, the two errors are considered out- side the scope and left to future work, despite the fact that they are widely found and bound to CSC task in Chinese industrial scenario, such as Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR). 2) Most existing CSC methods focus on either detector or corrector and train different mod- els for each one, respectively, leading to in- sufficiency of parameters sharing. To address these issues, we propose a novel model UMR- Spell to learn detection and correction parts together at the same time from a multi-task learning perspective by using a detection trans- mission self-attention matrix, and flexibly deal with both missing, redundant, and spelling er- rors through re-tagging rules. Furthermore, we build a new dataset ECMR-2023 containing five kinds of character-level errors to enrich the CSC task closer to real-world applications. Ex- periments on both SIGHAN benchmarks and ECMR-2023 demonstrate the significant effec- tiveness of UMRSpell over previous represen- tative baselines.</abstract>
<identifier type="citekey">he-etal-2023-umrspell</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.570</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.570</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10238</start>
<end>10250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction
%A He, Zheyu
%A Zhu, Yujin
%A Wang, Linlin
%A Xu, Liang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F he-etal-2023-umrspell
%X Chinese Spelling Correction (CSC) is the task of detecting and correcting misspelled charac- ters in Chinese texts. As an important step for various downstream tasks, CSC confronts two challenges: 1) Character-level errors consist not only of spelling errors but also of missing and redundant ones that cause variable length between input and output texts, for which most CSC methods could not handle well because of the consistence length of texts required by their inherent detection-correction framework. Con- sequently, the two errors are considered out- side the scope and left to future work, despite the fact that they are widely found and bound to CSC task in Chinese industrial scenario, such as Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR). 2) Most existing CSC methods focus on either detector or corrector and train different mod- els for each one, respectively, leading to in- sufficiency of parameters sharing. To address these issues, we propose a novel model UMR- Spell to learn detection and correction parts together at the same time from a multi-task learning perspective by using a detection trans- mission self-attention matrix, and flexibly deal with both missing, redundant, and spelling er- rors through re-tagging rules. Furthermore, we build a new dataset ECMR-2023 containing five kinds of character-level errors to enrich the CSC task closer to real-world applications. Ex- periments on both SIGHAN benchmarks and ECMR-2023 demonstrate the significant effec- tiveness of UMRSpell over previous represen- tative baselines.
%R 10.18653/v1/2023.acl-long.570
%U https://aclanthology.org/2023.acl-long.570
%U https://doi.org/10.18653/v1/2023.acl-long.570
%P 10238-10250
Markdown (Informal)
[UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction](https://aclanthology.org/2023.acl-long.570) (He et al., ACL 2023)
ACL