Chinese Discourse Relation Recognition Using Parallel Corpus

Though an important task in natural language processing, discourse relation recognition has not until recently received as much attention as it deserves, maybe due to its complexity. In Chinese, discourse relations are mostly implicit, making the task even harder. There are more explicit discourse relations in English than Chinese. In this paper, we propose a new approach to Chinese discourse relation recognition, which utilizes English-Chinese alignment corpus to discover implicit Chinese discourse relations. Results show our method achieves 60% accuracy in argument detection and 40% accuracy in discourse relation recognition.