This book presents a comprehensive overview of semi-supervised approaches to dependency parsing. Having become increasingly popular in recent years, one of the main reasons for their success is that they can make use of large unlabeled data together with relatively small labeled data and have shown their advantages in the context of dependency parsing for many languages. Various semi-supervised dependency parsing approaches have been proposed in recent works which utilize different types of information gleaned from unlabeled data. The book offers readers a comprehensive introduction to these approaches, making it ideally suited as a textbook for advanced undergraduate and graduate students and researchers in the fields of syntactic parsing and natural language processing.

Presents a comprehensive overview of semi-supervised approaches to dependency parsing Bridges the gap between small human-annotated training data and huge raw data for dependency parsing Explains why semi-supervised approaches are well suited to dependency parsing Clarifies the differences between the three levels of information for semi-supervised dependency parsing