@inproceedings{wei-etal-2024-training,
title = "Training a Better {C}hinese Spelling Correction Model via Prior-knowledge Guided Teacher",
author = "Wei, Chi and
Huang, Shaobin and
Li, Rongsheng and
Yan, Naiyu and
Wang, Rui",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.806",
pages = "13578--13589",
abstract = "Recent advancements in Chinese Spelling Correction (CSC) predominantly leverage pre-trained language models (PLMs). However, a notable challenge with fine-tuned PLM-based CSC models is their tendency to over-correct, leading to poor generalization for error patterns outside the standard distribution. To address this, we developed a teacher network guided by prior knowledge for distillation learning of CSC models. Unlike traditional teacher networks, which depend on task-related pre-training, our method infuses task-related prior information into the teacher network, offering guidance beyond mere labels to the student network. This strategy significantly enhances the CSC model{'}s language modeling capabilities, crucial for minimizing over-correction. Importantly, our approach is model-independent and the teacher network does not require task-related pre-training, making it broadly applicable for enhancing various PLM-based CSC models with minimal additional computational resources. Extensive experiments on widely used benchmarks demonstrate that our method achieves new state-of-the-art results. Additionally, we explored the potential of generalizing our method to other non-autoregressive text-generation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2024-training">
<titleInfo>
<title>Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided Teacher</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaobin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongsheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naiyu</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in Chinese Spelling Correction (CSC) predominantly leverage pre-trained language models (PLMs). However, a notable challenge with fine-tuned PLM-based CSC models is their tendency to over-correct, leading to poor generalization for error patterns outside the standard distribution. To address this, we developed a teacher network guided by prior knowledge for distillation learning of CSC models. Unlike traditional teacher networks, which depend on task-related pre-training, our method infuses task-related prior information into the teacher network, offering guidance beyond mere labels to the student network. This strategy significantly enhances the CSC model’s language modeling capabilities, crucial for minimizing over-correction. Importantly, our approach is model-independent and the teacher network does not require task-related pre-training, making it broadly applicable for enhancing various PLM-based CSC models with minimal additional computational resources. Extensive experiments on widely used benchmarks demonstrate that our method achieves new state-of-the-art results. Additionally, we explored the potential of generalizing our method to other non-autoregressive text-generation tasks.</abstract>
<identifier type="citekey">wei-etal-2024-training</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.806</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13578</start>
<end>13589</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided Teacher
%A Wei, Chi
%A Huang, Shaobin
%A Li, Rongsheng
%A Yan, Naiyu
%A Wang, Rui
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F wei-etal-2024-training
%X Recent advancements in Chinese Spelling Correction (CSC) predominantly leverage pre-trained language models (PLMs). However, a notable challenge with fine-tuned PLM-based CSC models is their tendency to over-correct, leading to poor generalization for error patterns outside the standard distribution. To address this, we developed a teacher network guided by prior knowledge for distillation learning of CSC models. Unlike traditional teacher networks, which depend on task-related pre-training, our method infuses task-related prior information into the teacher network, offering guidance beyond mere labels to the student network. This strategy significantly enhances the CSC model’s language modeling capabilities, crucial for minimizing over-correction. Importantly, our approach is model-independent and the teacher network does not require task-related pre-training, making it broadly applicable for enhancing various PLM-based CSC models with minimal additional computational resources. Extensive experiments on widely used benchmarks demonstrate that our method achieves new state-of-the-art results. Additionally, we explored the potential of generalizing our method to other non-autoregressive text-generation tasks.
%U https://aclanthology.org/2024.findings-acl.806
%P 13578-13589
Markdown (Informal)
[Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided Teacher](https://aclanthology.org/2024.findings-acl.806) (Wei et al., Findings 2024)
ACL