Dependency parsing for Chinese long sentence: A second-stage main structure parsing method

This paper explores the problem of parsing Chinese long sentences. Inspired by human sentence processing, a second-stage parsing method, referred as main structure parsing in this paper, are proposed to improve the parsing performance as well as maintaining its high accuracy and efficiency on Chinese long sentences. Three different methods have attempted in this paper and the result shows that the best performance comes from the method using Chinese comma as the boundary of the sub sentence. According to our experiment about testing on the Chinese dependency Treebank 1.0 data, it improves long dependency accuracy by around 6.0% than the baseline parser and 3.2% than the previous best model.