Inductive Dependency Parsing

ISBN-13: 9781402048883 / Angielski / Twarda / 2006 / 212 str.

Joakim Nivre

Opis

This book describes the framework of inductive dependency parsing, a methodology for robust and efficient syntactic analysis of unrestricted natural language text. Coverage includes a theoretical analysis of central models and algorithms, and an empirical evaluation of memory-based dependency parsing using data from Swedish and English. A one-stop reference to dependency-based parsing of natural language, it will interest researchers and system developers in language technology, and is suitable for graduate or advanced undergraduate courses.

Recenzje

From the reviews:

"The book demonstrates Nivre's impressive ability to explain dependency grammar and dependency parsing clearly and succinctly to a wide audience. ... The logical progression and the clarity with which this is done is one of the many strengths of this book. ... Get Nivre's book; read it; and enjoy it! The excellent and thorough reference list alone is worth it, constituting a good ten percent of the book." (Christer Samuelsson, Computational Linguistics, Vol. 33 (2), 2007)

Spis treści

Natural Language Parsing.- Dependency Parsing.- Inductive Dependency Parsing.- Treebank Parsing.- Conclusion.

Blurb

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.