Vietnamese Syntactic Dependency Parsing

Abstract

Dependency parsing has become an important line of research in natural language processing in recent years. This is due to its usefulness in a wide variety of real world applications. In this thesis, we focus on develop a high-accuracy parser for Vietnamese language. First, we present the improvement of Vietnamese dependency parsing using distributed word representations. Second, we conduct experiments to find efficient techniques for dependency parsing. Finally, we develop of a state-of-the-art dependency parser on the Vietnamese Dependency Treebank. Our parser achieves an accuracy of 76.3% of unlabeled attachment score or 69.23% of labelled attachment score. This is the most accurate dependency parser for the Vietnamese language in comparison to others, which are trained and tested on the same dependency Treebank. The distributed word representations are produced by two recent unsupervised learning models, which are the Skip-gram model and the GloVe model. We also show that distributed representations produced by the GloVe model are better than those produced by the Skip-gram model when being used in dependency parsing. Our dependency parsing system, including software, corpus and distributed word representations, is released as an open source project.