A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check

TL;DR

This paper introduces a modular detection-and-reasoning component for Chinese Spelling Check that enhances existing models by leveraging language knowledge, improving performance and interpretability through task decomposition.

Contribution

It proposes a plug-and-play detection-and-reasoning module for CSC that can be integrated with existing models, improving their effectiveness and interpretability.

Findings

The module boosts performance of state-of-the-art CSC models.

The detection-and-reasoning module benefits multiple models.

The approach enhances interpretability through task decomposition.

Abstract

In recent years, Chinese Spelling Check (CSC) has been greatly improved by designing task-specific pre-training methods or introducing auxiliary tasks, which mostly solve this task in an end-to-end fashion. In this paper, we propose to decompose the CSC workflow into detection, reasoning, and searching subtasks so that the rich external knowledge about the Chinese language can be leveraged more directly and efficiently. Specifically, we design a plug-and-play detection-and-reasoning module that is compatible with existing SOTA non-autoregressive CSC models to further boost their performance. We find that the detection-and-reasoning module trained for one model can also benefit other models. We also study the primary interpretability provided by the task decomposition. Extensive experiments and detailed analyses demonstrate the effectiveness and competitiveness of the proposed module.