DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check

• URL: http://arxiv.org/abs/2412.12863v1
• Date: Tue, 17 Dec 2024 12:44:06 GMT
• Title: DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check
• Authors: Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang,
• Abstract summary: We propose a light-weight plug-and-play DISC (i.e., decoding intervention with similarity of characters) module for Chinese spelling check (CSC) models. DISC measures phonetic and glyph similarities between characters and incorporates this similarity information only during the inference phase. Experiments on three CSC benchmarks demonstrate that our proposed method significantly improves model performance, approaching and even surpassing the current state-of-the-art models.
• Score: 37.44133266050293
• License:
• Abstract: One key characteristic of the Chinese spelling check (CSC) task is that incorrect characters are usually similar to the correct ones in either phonetics or glyph. To accommodate this, previous works usually leverage confusion sets, which suffer from two problems, i.e., difficulty in determining which character pairs to include and lack of probabilities to distinguish items in the set. In this paper, we propose a light-weight plug-and-play DISC (i.e., decoding intervention with similarity of characters) module for CSC models.DISC measures phonetic and glyph similarities between characters and incorporates this similarity information only during the inference phase. This method can be easily integrated into various existing CSC models, such as ReaLiSe, SCOPE, and ReLM, without additional training costs. Experiments on three CSC benchmarks demonstrate that our proposed method significantly improves model performance, approaching and even surpassing the current state-of-the-art models.

Related papers

• EdaCSC: Two Easy Data Augmentation Methods for Chinese Spelling Correction [0.0]
  Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in Chinese sentences caused by phonetic or visual similarities. We propose two data augmentation methods to address these limitations. Firstly, we augment the dataset by either splitting long sentences into shorter ones or reducing typos in sentences with multiple typos.
  arXiv  Detail & Related papers  (2024-09-08T14:29:10Z)
• Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition [28.93482989766411]
  We propose a novel method that enriches the character features to enhance discriminability of characters. CACE introduces a decay matrix in each block to explicitly guide the attention region for each token. I2CL improves the discnative capability of features by learning a long-term memory unit for each character category.
  arXiv  Detail & Related papers  (2024-07-08T02:33:29Z)
• C-LLM: Learn to Check Chinese Spelling Errors Character by Character [61.53865964535705]
  We propose C-LLM, a Large Language Model-based Chinese Spell Checking method that learns to check errors Character by Character. C-LLM achieves an average improvement of 10% over existing methods.
  arXiv  Detail & Related papers  (2024-06-24T11:16:31Z)
• PRIME: Prioritizing Interpretability in Failure Mode Extraction [49.93565079216376]
  We study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. We propose a novel approach that prioritizes interpretability in this problem. Our method successfully identifies failure modes and generates high-quality text descriptions associated with them.
  arXiv  Detail & Related papers  (2023-09-29T22:00:12Z)
• Chinese Spelling Correction as Rephrasing Language Model [63.65217759957206]
  We study Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CSC as a sequence tagging task and fine-tune BERT-based models on sentence pairs. We propose Rephrasing Language Model (ReLM), where the model is trained to rephrase the entire sentence by infilling additional slots, instead of character-to-character tagging.
  arXiv  Detail & Related papers  (2023-08-17T06:04:28Z)
• CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers [62.61866477815883]
  We present CSCD-NS, the first Chinese spelling check dataset designed for native speakers. CSCD-NS is ten times larger in scale and exhibits a distinct error distribution. We propose a novel method that simulates the input process through an input method.
  arXiv  Detail & Related papers  (2022-11-16T09:25:42Z)
• Contextual Similarity is More Valuable than Character Similarity: Curriculum Learning for Chinese Spell Checking [26.93594761258908]
  Chinese Spell Checking (CSC) task aims to detect and correct Chinese spelling errors. To make better use of contextual similarity, we propose a simple yet effective curriculum learning framework for the CSC task. With the help of our designed model-agnostic framework, existing CSC models will be trained from easy to difficult as humans learn Chinese characters.
  arXiv  Detail & Related papers  (2022-07-17T03:12:27Z)
• Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models [51.744357472072416]
  We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances. Experimental results show that such an adversarial training method combined with the pretraining strategy can improve both the generalization and robustness of multiple CSC models.
  arXiv  Detail & Related papers  (2021-05-31T09:17:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.