An Adversarial Multi-Task Learning Method for Chinese Text Correction with Semantic Detection

TL;DR

This paper introduces an adversarial multi-task learning approach combining masked and scoring language models, enhanced by Monte Carlo tree search, to improve Chinese text correction with semantic detection, achieving better semantic rationality.

Contribution

It proposes a novel adversarial multi-task learning framework integrating semantic detection for Chinese text correction, utilizing Monte Carlo tree search for efficiency.

Findings

Outperforms five comparable methods on three datasets.

Achieves improved semantic rationality in Chinese text correction.

Demonstrates effective modeling of character polysemy in context.

Abstract

Text correction, especially the semantic correction of more widely used scenes, is strongly required to improve, for the fluency and writing efficiency of the text. An adversarial multi-task learning method is proposed to enhance the modeling and detection ability of character polysemy in Chinese sentence context. Wherein, two models, the masked language model and scoring language model, are introduced as a pair of not only coupled but also adversarial learning tasks. Moreover, the Monte Carlo tree search strategy and a policy network are introduced to accomplish the efficient Chinese text correction task with semantic detection. The experiments are executed on three datasets and five comparable methods, and the experimental results show that our method can obtain good performance in Chinese text correction task for better semantic rationality.