Dependency Parsing

Dependency Parsing

Sandra Kubler, Ryan McDonald, Joakim Nivre
ISBN: 9781598295962 | PDF ISBN: 9781598295979
Copyright © 2009 | 127 Pages | Publication Date: 01/01/2009

BEFORE YOU ORDER: You may have Academic or Corporate access to this title. Click here to find out: 10.2200/S00169ED1V01Y200901HLT002

Ordering Options: Paperback $30.00   E-book $24.00   Paperback & E-book Combo $37.50

Why pay full price? Members receive 15% off all orders.
Learn More Here

Read Our Digital Content License Agreement (pop-up)

Purchasing Options:

Dependency-based methods for syntactic parsing have become increasingly popular in natural language processing in recent years. This book gives a thorough introduction to the methods that are most widely used today. After an introduction to dependency grammar and dependency parsing, followed by a formal characterization of the dependency parsing problem, the book surveys the three major classes of parsing models that are in current use: transition-based, graph-based, and grammar-based models. It continues with a chapter on evaluation and one on the comparison of different methods, and it closes with a few words on current trends and future prospects of dependency parsing. The book presupposes a knowledge of basic concepts in linguistics and computer science, as well as some knowledge of parsing methods for constituency-based representations.

Table of Contents

Dependency Parsing
Transition-Based Parsing
Graph-Based Parsing
Grammar-Based Parsing
Final Thoughts

About the Author(s)

Sandra Kubler, Department of Linguistics, Indiana University
Sandra Kubler is Assistant Professor of Computational Linguistics at Indiana University, where she has worked since 2006. She received her M.A. from the University of Trier and her Ph.D. in Computational Linguistics from the University of Tubingen. Sandra’s research focuses on data-driven methods for syntactic and semantic processing. For her dissertation work, she developed a novel memory-based approach to parsing spontaneous speech. This parser was integrated into the Verbmobil speech-to-speech translation system. Sandra is currently interested in parsing German, a non-configurational language, for which several treebanks are available. Her research focuses on comparisons between constituent-based and dependency-based parsing and comparisons of how different annotation schemes influence parsing results.

Ryan McDonald, Google Research
Ryan McDonald is a Senior Research Scientist at Google, Inc., where he has worked since 2006. He received his B.Sc. from the University of Toronto and his Ph.D. in Computer and Information Science from the University of Pennsylvania. Ryan's research focuses on learning and inference algorithms for parsing and summarizing natural language. His dissertation work advanced the theoretical and empirical foundations for modern graph-based dependency parsers. The result of this work was the MSTParser software package, which tied for the most accurate system in the first shared task on multilingual dependency parsing at the Conference on Computational Natural Language Learning in 2006. Since arriving at Google, Ryan's research has focused on opinion mining, including methods for automatically identifying opinions, extracting relevant attributes, and building faceted summaries from large text collections.

Joakim Nivre, Department of Linguistics and Philology, Uppsala University and School of Mathematics and System Engineering, Vaxjo University
Joakim Nivre is Professor of Computational Linguistics at Uppsala University (since 2008) and at Vaxjo University (since 2002). He holds a Ph.D. in General Linguistics from the University of Gothenburg and a Ph.D. in Computer Science from Vaxjo University. Joakim's research focuses on data-driven methods for natural language processing, in particular for syntactic and semantic analysis. He is one of the main developers of the transition-based approach to data-driven dependency parsing, described in his 2006 book Inductive Dependency Parsing and implemented in the MaltParser system. Systems developed using MaltParser were tied for first place in the shared tasks on multilingual dependency parsing at the Conference on Computational Natural Language Learning in both 2006 and 2007. Joakim’s current research interests include the analysis of mildly non-projective dependency structures, the integration of morphological and syntactic processing for richly inflected languages, and the modeling of human sentence processing.

Browse by Subject
Case Studies in Engineering
ACM Books
IOP Concise Physics
SEM Books
0 items

Note: Registered customers go to: Your Account to subscribe.

E-Mail Address:

Your Name: