Bi-DCSpell: A Bi-directional Detector-Corrector Interactive Framework for Chinese Spelling Check

TL;DR

Bi-DCSpell introduces a novel bi-directional interactive framework for Chinese Spelling Check, enhancing detection and correction by enabling mutual feature learning, leading to improved performance on standard datasets.

Contribution

It proposes a new bi-directional detection-correction framework with interactive learning modules, addressing the limitations of previous unidirectional approaches.

Findings

Achieves robust correction performance on benchmark datasets.

Maintains satisfactory detection accuracy.

Outperforms existing CSC methods in experiments.

Abstract

Chinese Spelling Check (CSC) aims to detect and correct potentially misspelled characters in Chinese sentences. Naturally, it involves the detection and correction subtasks, which interact with each other dynamically. Such interactions are bi-directional, i.e., the detection result would help reduce the risk of over-correction and under-correction while the knowledge learnt from correction would help prevent false detection. Current CSC approaches are of two types: correction-only or single-directional detection-to-correction interactive frameworks. Nonetheless, they overlook the bi-directional interactions between detection and correction. This paper aims to fill the gap by proposing a Bi-directional Detector-Corrector framework for CSC (Bi-DCSpell). Notably, Bi-DCSpell contains separate detection and correction encoders, followed by a novel interactive learning module facilitating bi-directional feature interactions between detection and correction to improve each other's representation learning. Extensive experimental results demonstrate a robust correction performance of Bi-DCSpell on widely used benchmarking datasets while possessing a satisfactory detection ability.