Dependency Parsing by Transformation and Combination

This study presents new language and treebank independent graph transformations that improve accuracy in data-driven dependency parsing. We show that individual generic graph transformations can increase accuracy across treebanks, but especially when they are combined using established parser combin...

Full description

Saved in:
Bibliographic Details
Published inAdvances in Natural Language Processing Vol. 5221; pp. 348 - 359
Main Authors Nilsson, Jens, Nivre, Joakim
Format Book Chapter Conference Proceeding
LanguageEnglish
Published Germany Springer Berlin / Heidelberg 2008
Springer Berlin Heidelberg
SeriesLecture Notes in Computer Science
Subjects
Computational linguistics
Datorlingvistik
Dependency Graph
Dependency Parsing
Generic Transformation
Graph Transformation
HUMANIORA och RELIGIONSVETENSKAP
HUMANITIES and RELIGION
Inverse Transformation
Language technology
Languages and linguistics
Linguistic subjects
Lingvistikämnen
Språkteknologi
Språkvetenskap
Online AccessGet full text

Cover

More Information
Summary:This study presents new language and treebank independent graph transformations that improve accuracy in data-driven dependency parsing. We show that individual generic graph transformations can increase accuracy across treebanks, but especially when they are combined using established parser combination techniques. The combination experiments also indicate that the presumed best way to combine parsers, using the highest scoring parsers, is not necessarily the best approach.
ISBN:3540852867
9783540852865
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-540-85287-2_33