Error-Robust Retrieval for Chinese Spelling Check

TL;DR

This paper introduces RERIC, a retrieval-based method that enhances Chinese Spelling Check models by leveraging multimodal representations and error-robust information, significantly improving performance on benchmark datasets.

Contribution

The paper proposes a plug-and-play retrieval approach with multimodal features and reranking for Chinese Spelling Check, addressing data limitations and improving robustness.

Findings

Achieves substantial improvements on SIGHAN benchmarks.

Effectively leverages training data with multimodal representations.

Enhances error robustness in Chinese Spelling Check models.

Abstract

Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts, which has a wide range of applications. However, it is confronted with the challenges of insufficient annotated data and the issue that previous methods may actually not fully leverage the existing datasets. In this paper, we introduce our plug-and-play retrieval method with error-robust information for Chinese Spelling Check (RERIC), which can be directly applied to existing CSC models. The datastore for retrieval is built completely based on the training data, with elaborate designs according to the characteristics of CSC. Specifically, we employ multimodal representations that fuse phonetic, morphologic, and contextual information in the calculation of query and key during retrieval to enhance robustness against potential errors. Furthermore, in order to better judge the retrieved candidates, the n-gram surrounding the token to be checked is regarded as the value and utilized for specific reranking. The experiment results on the SIGHAN benchmarks demonstrate that our proposed method achieves substantial improvements over existing work.