Chinese Discourse Segmentation Using Bilingual Discourse Commonality

TL;DR

This paper introduces a bilingual adversarial neural network approach for Chinese discourse segmentation, leveraging English data to improve Chinese EDU boundary detection, especially with limited Chinese labeled data.

Contribution

It proposes a novel adversarial framework that extracts language-independent features from bilingual data for Chinese discourse segmentation, addressing the scarcity of Chinese labeled data.

Findings

Outperforms baseline models in Chinese discourse segmentation

Effectively leverages English labeled data for Chinese EDU segmentation

Learns efficient Chinese-specific features from limited data

Abstract

Discourse segmentation aims to segment Elementary Discourse Units (EDUs) and is a fundamental task in discourse analysis. For Chinese, previous researches identify EDUs just through discriminating the functions of punctuations. In this paper, we argue that Chinese EDUs may not end at the punctuation positions and should follow the definition of EDU in RST-DT. With this definition, we conduct Chinese discourse segmentation with the help of English labeled data.Using discourse commonality between English and Chinese, we design an adversarial neural network framework to extract common language-independent features and language-specific features which are useful for discourse segmentation, when there is no or only a small scale of Chinese labeled data available. Experiments on discourse segmentation demonstrate that our models can leverage common features from bilingual data, and learn efficient Chinese-specific features from a small amount of Chinese labeled data, outperforming the baseline models.