Transition-Based Techniques for Non-Projective Dependency Parsing

We present an empirical evaluation of three methods for the treatment of non-projective structures in transition-based dependency parsing: pseudo-projective parsing, non-adjacent arc transitions, and online reordering. We compare both the theoretical coverage and the empirical performance of these...

Full description

Saved in:
Bibliographic Details
Main Authors: Marco Kuhlmann, Joakim Nivre
Format: Article
Language:English
Published: Linköping University Electronic Press 2010-10-01
Series:Northern European Journal of Language Technology
Online Access:https://nejlt.ep.liu.se/article/view/1651
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590612542521344
author Marco Kuhlmann
Joakim Nivre
author_facet Marco Kuhlmann
Joakim Nivre
author_sort Marco Kuhlmann
collection DOAJ
description We present an empirical evaluation of three methods for the treatment of non-projective structures in transition-based dependency parsing: pseudo-projective parsing, non-adjacent arc transitions, and online reordering. We compare both the theoretical coverage and the empirical performance of these methods using data from Czech, English and German. The results show that although online reordering is the only method with complete theoretical coverage, all three techniques exhibit high precision but somewhat lower recall on non-projective dependencies and can all improve overall parsing accuracy provided that non-projective dependencies are frequent enough. We also find that the use of non-adjacent arc transitions may lead to a drop in accuracy on projective dependencies in the presence of long-distance non-projective dependencies, an effect that is not found for the two other techniques.
format Article
id doaj-art-82db2367c1334526952b8b4141c45405
institution Kabale University
issn 2000-1533
language English
publishDate 2010-10-01
publisher Linköping University Electronic Press
record_format Article
series Northern European Journal of Language Technology
spelling doaj-art-82db2367c1334526952b8b4141c454052025-01-23T10:36:34ZengLinköping University Electronic PressNorthern European Journal of Language Technology2000-15332010-10-01210.3384/nejlt.2000-1533.10211Transition-Based Techniques for Non-Projective Dependency ParsingMarco Kuhlmann0Joakim Nivre1Uppsala University. Department of Linguistics and Philology, SwedenUppsala University. Department of Linguistics and Philology, Sweden We present an empirical evaluation of three methods for the treatment of non-projective structures in transition-based dependency parsing: pseudo-projective parsing, non-adjacent arc transitions, and online reordering. We compare both the theoretical coverage and the empirical performance of these methods using data from Czech, English and German. The results show that although online reordering is the only method with complete theoretical coverage, all three techniques exhibit high precision but somewhat lower recall on non-projective dependencies and can all improve overall parsing accuracy provided that non-projective dependencies are frequent enough. We also find that the use of non-adjacent arc transitions may lead to a drop in accuracy on projective dependencies in the presence of long-distance non-projective dependencies, an effect that is not found for the two other techniques. https://nejlt.ep.liu.se/article/view/1651
spellingShingle Marco Kuhlmann
Joakim Nivre
Transition-Based Techniques for Non-Projective Dependency Parsing
Northern European Journal of Language Technology
title Transition-Based Techniques for Non-Projective Dependency Parsing
title_full Transition-Based Techniques for Non-Projective Dependency Parsing
title_fullStr Transition-Based Techniques for Non-Projective Dependency Parsing
title_full_unstemmed Transition-Based Techniques for Non-Projective Dependency Parsing
title_short Transition-Based Techniques for Non-Projective Dependency Parsing
title_sort transition based techniques for non projective dependency parsing
url https://nejlt.ep.liu.se/article/view/1651
work_keys_str_mv AT marcokuhlmann transitionbasedtechniquesfornonprojectivedependencyparsing
AT joakimnivre transitionbasedtechniquesfornonprojectivedependencyparsing