mlsanityData to 7 Oct 2026

Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking

arXiv 2210.10320 ↗First posted 19 Oct 2022cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors. Recent researches start from the pretrained knowledge of language models and take multimodal information into CSC models to improve the performance. However, they overlook the rich knowledge in the dictionary, the reference book where one can learn how one character should be pronounced, written, and used. In this paper, we propose the LEAD framework, which renders the CSC model to learn heterogeneous knowledge from the dictionary in terms of phonetics, vision, and meaning. LEAD first constructs positive and negative samples according to the knowledge of character phonetics, glyphs, and definitions in the dictionary. Then a unified contrastive learning-based training scheme is employed to refine the representations of the CSC models. Extensive experiments and detailed analyses on the SIGHAN benchmark datasets demonstrate the effectiveness of our proposed methods.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

20 of 39 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  9. 2017Decoupled Weight Decay Regularizationcited by 1,722
  10. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 262
  11. 2017Gate-Variants of Gated Recurrent Unit (GRU) Neural Networkscited by 239
  12. 2019ERNIE 2.0: A Continual Pre-training Framework for Language Understandingcited by 230
8 more
  1. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
  2. 2020Spelling Error Correction with Soft-Masked BERTcited by 90
  3. 2020ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learningcited by 72
  4. 2020SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Checkcited by 57
  5. 2022The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checkingcited by 56
  6. 2021Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checkingcited by 52
  7. 2022Contrastive Learning with Hard Negative Entities for Entity Set Expansioncited by 26
  8. 2021Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Modelscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 9; 2025: 7; 2026: 2.

31 papers.

Sort:

By area:

  1. 2023On the (In)Effectiveness of Large Language Models for Chinese Text Correctioncited by 53
  2. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 21
  3. 2025DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokenscited by 21
  4. 2023A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Checkcited by 15
  5. 2023Disentangled Phonetic Representation for Chinese Spelling Correctioncited by 14
  6. 2023Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correctioncited by 13
  7. 2023MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entitiescited by 13
  8. 2023EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Datacited by 9
  9. 2024Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correctioncited by 9
  10. 2026Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understandingcited by 6
  11. 2023CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correctioncited by 5
  12. 2024Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Frameworkcited by 4
19 more
  1. 2025From Token to Line: Enhancing Code Generation with a Long-Term Perspectivecited by 4
  2. 2024Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansioncited by 3
  3. 2024Loss-Aware Curriculum Learning for Chinese Grammatical Error Correctioncited by 3
  4. 2025MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuningcited by 3
  5. 2026TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoningcited by 3
  6. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  7. 2023MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correctioncited by 2
  8. 2024UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entitiescited by 2
  9. 2024Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correctioncited by 2
  10. 2025Chinese Spelling Correction: A Comprehensive Survey of Progress, Challenges, and Opportunitiescited by 2
  11. 2025Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learningcited by 2
  12. 2023Prompt Learning With Knowledge Memorizing Prototypes For Generalized Few-Shot Intent Detectioncited by 1
  13. 2024Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correctioncited by 1
  14. 2025Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correctioncited by 1
  15. 2022A Chinese Spelling Check Framework Based on Reverse Contrastive Learningcited by 0
  16. 2023An Anchor Learning Approach for Citation Field Learningcited by 0
  17. 2024A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correctioncited by 0
  18. 2024EdaCSC: Two Easy Data Augmentation Methods for Chinese Spelling Correctioncited by 0
  19. 2025CL2GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correctioncited by 0