Chinese Discourse Segmentation Using Bilingual Discourse Commonality
This work addresses discourse segmentation for Chinese, a domain-specific NLP task, by introducing a bilingual approach that improves performance with limited labeled data, though it is incremental in method.
The paper tackled Chinese discourse segmentation by redefining Elementary Discourse Units (EDUs) based on RST-DT and using bilingual data to extract common and language-specific features via an adversarial neural network, resulting in models that outperformed baselines by leveraging English labeled data and minimal Chinese annotations.
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.