uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
Inductive Dependency Parsing
Uppsala University, Humanistisk-samhällsvetenskapliga vetenskapsområdet, Faculty of Languages, Department of Linguistics and Philology. Datorlingvistik.
2006 (English)Book (Refereed)
Abstract [en]

This book provides an in-depth description of the framework of inductive dependency parsing, a methodology for robust and efficient syntactic analysis of unrestricted natural language text. This methodology is based on two essential components: dependency-based syntactic representations and a data-driven approach to syntactic parsing. More precisely, it is based on a deterministic parsing algorithm in combination with inductive machine learning to predict the next parser action.

The book includes a theoretical analysis of all central models and algorithms, as well as a thorough empirical evaluation of memory-based dependency parsing, using data from Swedish and English. Offering the reader a one-stop reference to dependency-based parsing of natural language, it is intended for researchers and system developers in the language technology field, and is also suited for graduate or advanced undergraduate education.

Place, publisher, year, edition, pages
Springer, Dordrecht , 2006. , 216 p.
, Text, Speech and Language Technology, 34
Keyword [en]
syntactic parsing, dependency parsing, machine learning, memory-based learning
National Category
Language Technology (Computational Linguistics)
URN: urn:nbn:se:uu:diva-21995ISBN: 1-4020-4888-2OAI: oai:DiVA.org:uu-21995DiVA: diva2:49768
Available from: 2007-01-09 Created: 2007-01-09

Open Access in DiVA

No full text

Other links


Search in DiVA

By author/editor
Nivre, Joakim
By organisation
Department of Linguistics and Philology
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 183 hits
ReferencesLink to record
Permanent link

Direct link