Dependency Parsing

Dependency parsing is a form of syntactic parsing of natural language based on the theoretical tradition of dependency grammar. It has recently gained widespread interest in the computational linguistics community and has been used for applications such as information extraction, machine translation...

Full description

Saved in:
Bibliographic Details
Published in:Language and linguistics compass Vol. 4; no. 3; pp. 138 - 152
Main Author: Nivre, Joakim
Format: Journal Article
Language:English
Published: Oxford, UK Blackwell Publishing Ltd 01.03.2010
Subjects:
Computational Linguistics
Computer Generated Language Analysis
Datorlingvistik
Dependency Grammar
HUMANIORA och RELIGIONSVETENSKAP
HUMANITIES and RELIGION
Language technology
Languages and linguistics
Linguistic subjects
Lingvistikämnen
Parsing
Språkteknologi
Språkvetenskap
Syntax
ISSN:1749-818X, 1749-818X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Dependency parsing is a form of syntactic parsing of natural language based on the theoretical tradition of dependency grammar. It has recently gained widespread interest in the computational linguistics community and has been used for applications such as information extraction, machine translation and question answering. In this article, we review the current state of the art in dependency parsing, starting with a characterization of the basic problem and some motivation for why dependency parsing may be a useful alternative to other forms of syntactic parsing. The major part of the article is devoted to an examination of the four main approaches that exist in the field today: context‐free dependency parsing, constraint dependency parsing, graph‐based dependency parsing, and transition‐based dependency parsing. Each approach is described in detail and its strengths and weaknesses are highlighted.
Bibliography:ark:/67375/WNG-XM6F60RZ-7
istex:A51C443C6698249C7F7DA79010AC1234B403388A
ArticleID:LNC3187
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1749-818X
1749-818X
DOI:10.1111/j.1749-818X.2010.00187.x