mlsanityData to 7 Oct 2026

The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking

arXiv 2203.00991 ↗First posted 2 Mar 2022cs.CLcited by 56

Not on the map. Why?

Abstract (arXiv)

Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors, which are mainly caused by the phonological or visual similarity. Recently, pre-trained language models (PLMs) promote the progress of CSC task. However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task. PLMs focus on the semantics in text and tend to correct the erroneous characters to semantically proper or commonly used ones, but these aren't the ground-truth corrections. To address this issue, we propose an Error-driven COntrastive Probability Optimization (ECOPO) framework for CSC task. ECOPO refines the knowledge representations of PLMs, and guides the model to avoid predicting these common characters through an error-driven way. Particularly, ECOPO is model-agnostic and it can be combined with existing CSC methods to achieve better performance. Extensive experiments and detailed analyses on SIGHAN datasets demonstrate that ECOPO is simple yet effective.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 13 of its 44 references that are in the map. First posted on arXiv 2 Mar 2022.

Builds on

13 of 44 references.

References · 13

  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. 2020Supervised Contrastive Learningcited by 2,803
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  6. 2017Decoupled Weight Decay Regularizationcited by 1,722
  7. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 262
  8. 2020Spelling Error Correction with Soft-Masked BERTcited by 90
  9. 2020SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Checkcited by 57
  10. 2021Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checkingcited by 52
  11. 2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
  12. 2020Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Modelscited by 49
1 more
  1. 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: 12; 2023: 18; 2024: 11; 2025: 10; 2026: 5.

56 papers.

Sort:

By area:

  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  3. 2023On the (In)Effectiveness of Large Language Models for Chinese Text Correctioncited by 53
  4. 2023LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzlescited by 41
  5. 2022Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checkingcited by 31
  6. 2022Contrastive Learning with Hard Negative Entities for Entity Set Expansioncited by 26
  7. 2022General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretrainingcited by 25
  8. 2022Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correctioncited by 25
  9. 2024When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Modelscited by 22
  10. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 21
  11. 2025DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokenscited by 21
  12. 2023A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Checkcited by 15
38 more
  1. 2022Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checkingcited by 14
  2. 2023Disentangled Phonetic Representation for Chinese Spelling Correctioncited by 14
  3. 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learningcited by 14
  4. 2023Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correctioncited by 13
  5. 2023MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entitiescited by 13
  6. 2022Embracing Ambiguity: Improving Similarity-oriented Tasks with Contextual Synonym Knowledgecited by 11
  7. 2022Active Relation Discovery: Towards General and Label-aware Open Relation Extractioncited by 10
  8. 2024Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correctioncited by 9
  9. 2022MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correctioncited by 8
  10. 2025AdmTree: Compressing Lengthy Context with Adaptive Semantic Treescited by 7
  11. 2026EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configurationcited by 7
  12. 2023ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understandingcited by 6
  13. 2026Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understandingcited by 6
  14. 2023CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correctioncited by 5
  15. 2022Error-Robust Retrieval for Chinese Spelling Checkcited by 4
  16. 2024Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Frameworkcited by 4
  17. 2025From Token to Line: Enhancing Code Generation with a Long-Term Perspectivecited by 4
  18. 2022Focus Is What You Need For Chinese Grammatical Error Correctioncited by 3
  19. 2023From Retrieval to Generation: Efficient and Effective Entity Set Expansioncited by 3
  20. 2024Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Modelcited by 3
  21. 2024Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansioncited by 3
  22. 2024Loss-Aware Curriculum Learning for Chinese Grammatical Error Correctioncited by 3
  23. 2025MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuningcited by 3
  24. 2026TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoningcited by 3
  25. 2026Latent Visual Cache for Video Reasoningcited by 3
  26. 2023Multi-source Education Knowledge Graph Construction and Fusion for College Curriculacited by 2
  27. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  28. 2023MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correctioncited by 2
  29. 2024UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entitiescited by 2
  30. 2025Attention Basin: Why Contextual Position Matters in Large Language Modelscited by 2
  31. 2025Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learningcited by 2
  32. 2022AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applicationscited by 1
  33. 2023Investigating Graph Structure Information for Entity Alignment with Dangling Casescited by 1
  34. 2023Prompt Learning With Knowledge Memorizing Prototypes For Generalized Few-Shot Intent Detectioncited by 1
  35. 2024Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correctioncited by 1
  36. 2025Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correctioncited by 1
  37. 2025Contextualized Token Discrimination for Speech Search Query Correctioncited by 1
  38. 2026Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoningcited by 1

50 most cited of 56 All 56 (JSON)