EMNLP Findings2023
A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check
Haojing Huang, Jingheng Ye, Qingyu Zhou, Yinghui Li, Yangning Li, Feng Zhou, Hai-Tao Zheng
Abstract
In recent years, Chinese Spelling Check (CSC) has been greatly improved by designing taskspecific pre-training methods or introducing auxiliary tasks, which mostly solve this task in an end-to-end fashion. In this paper, we propose to decompose the CSC workflow into detection, reasoning, and searching subtasks so that the rich external knowledge about the Chinese language can be leveraged more directly and efficiently. Specifically, we design a plug-and-play detection-and-reasoning module that is compatible with existing SOTA nonautoregressive CSC models to further boost their performance. We find that the detectionand-reasoning module trained for one model can also benefit other models. We also study the primary interpretability provided by the task decomposition. Extensive experiments 1 and detailed analyses demonstrate the effectiveness and competitiveness of the proposed module.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking cites ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding
- Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking cites SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
- Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking cites Spelling Error Correction with Soft-Masked BERT
- Revisiting Pre-Trained Models for Chinese Natural Language Processing cites ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding
- Mixture of Small and Large Models for Chinese Spelling Check cites Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
- Mixture of Small and Large Models for Chinese Spelling Check cites SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
- Mixture of Small and Large Models for Chinese Spelling Check cites Spelling Error Correction with Soft-Masked BERT
- Mixture of Small and Large Models for Chinese Spelling Check cites ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs
- Mixture of Small and Large Models for Chinese Spelling Check cites DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check
- CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction cites EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction
- ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs cites Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
- ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs cites Spelling Error Correction with Soft-Masked BERT
- DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check cites Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
- DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check cites SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
- DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check cites Spelling Error Correction with Soft-Masked BERT
Cited by top-tier papers5
- Mixture of Small and Large Models for Chinese Spelling CheckZiheng Qiao, Houquan Zhou, Zhenghua LiACL 2025 · 4 citations
- EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error CorrectionJingheng Ye, Shang Qin, Yinghui Li, Xuxin Cheng et al.AAAI 2025 · 3 citations
- ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMsChangchun Liu, Kai Zhang, Junzhe Jiang, Zirui Liu et al.EMNLP 2024 · 3 citations
- CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error CorrectionJingheng Ye, Zishan Xu, Yinghui Li, Linlin Song et al.ACL 2025
- DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling CheckZiheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li et al.ACL 2025
Builds on21
- ERNIE 2.0: A Continual Pre-Training Framework for Language UnderstandingYu Sun, Shuohuan Wang, Yu-Kun Li, Shikun Feng et al.AAAI 2020 · 885 citations
- Revisiting Pre-Trained Models for Chinese Natural Language ProcessingYiming Cui, Wanxiang Che, Ting Liu, Bing Qin et al.EMNLP Findings 2020 · 866 citations
- Spelling Error Correction with Soft-Masked BERTShaohua Zhang, Haoran Huang, Jicong Liu, Hang LiACL 2020 · 204 citations
- SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling CheckXingyi Cheng, Weidi Xu, Kunlong Chen, Shaohua Jiang et al.ACL 2020 · 139 citations
- Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell CheckingHeng-Da Xu, Zhongli Li, Qingyu Zhou, Chao Li et al.ACL Findings 2021 · 91 citations
Related papers
- Correcting Chinese Spelling Errors with Phonetic Pre-trainingRuiqing Zhang, Chao Pang, Chuanqiang Zhang, Shuohuan Wang et al.ACL Findings 2021 · 67 citations
- Dynamic Connected Networks for Chinese Spelling CheckBaoxin Wang, Wanxiang Che, Dayong Wu, Shijin Wang et al.ACL Findings 2021 · 55 citations
- PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling CorrectionShulin Liu, Tao Yang, Tianchi Yue, Feng Zhang et al.ACL 2021
- Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided TeacherChi Wei, Shaobin Huang, Rongsheng Li, Naiyu Yan et al.ACL Findings 2024 · 1 citation
- MDCSpell: A Multi-task Detector-Corrector Framework for Chinese Spelling CorrectionChenxi Zhu, Ziqiang Ying, Boyu Zhang, Feng MaoACL Findings 2022 · 39 citations
