mlsanityData to 7 Oct 2026

A Chinese Spelling Check Framework Based on Reverse Contrastive Learning

arXiv 2210.13823 ↗First posted 25 Oct 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Chinese spelling check is a task to detect and correct spelling mistakes in Chinese text. Existing research aims to enhance the text representation and use multi-source information to improve the detection and correction capabilities of models, but does not pay too much attention to improving their ability to distinguish between confusable words. Contrastive learning, whose aim is to minimize the distance in representation space between similar sample pairs, has recently become a dominant technique in natural language processing. Inspired by contrastive learning, we present a novel framework for Chinese spelling checking, which consists of three modules: language representation, spelling check and reverse contrastive learning. Specifically, we propose a reverse contrastive learning strategy, which explicitly forces the model to minimize the agreement between the similar examples, namely, the phonetically and visually confusable characters. Experimental results show that our framework is model-agnostic and could be combined with existing Chinese spelling check models to yield state-of-the-art performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 47 references that are in the map. First posted on arXiv 25 Oct 2022.

Builds on

18 of 47 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  7. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  8. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  9. 2020Spelling Error Correction with Soft-Masked BERTcited by 90
  10. 2020SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Checkcited by 57
  11. 2022The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checkingcited by 56
  12. 2021Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checkingcited by 52
6 more
  1. 2021Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classificationcited by 43
  2. 2022Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checkingcited by 31
  3. 2021CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Taskscited by 29
  4. 2022Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularitycited by 19
  5. 2022Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checkingcited by 14
  6. 2020Domain-shift Conditioning using Adaptable Filtering via Hierarchical Embeddings for Robust Chinese Spell Checkcited by 8

Built on by

Not cited yet.