Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Investigating multilingual dependency parsing

Johansson, Richard LU and Nugues, Pierre LU orcid (2006) Tenth Conference on Computational Natural Language Learning (CONLL-X) p.206-210
Abstract
In this paper, we describe a system for the CoNLL-X shared task of multilingual dependency parsing. It uses a baseline Nivre’s parser (Nivre, 2003) that first identifies the parse actions and then labels the dependency arcs. These two steps are implemented as SVM classifiers using LIBSVM. Features take into account the static context as well as relations dynamically built during parsing.

We experimented two main additions to our implementation of Nivre’s parser: N-best search and bidirectional parsing. We trained the parser in both left-right and right-left directions and we combined the results. To construct a single-head, rooted, and cycle-free tree, we applied the Chu-Liu/Edmonds optimization algorithm. We ran the same... (More)
In this paper, we describe a system for the CoNLL-X shared task of multilingual dependency parsing. It uses a baseline Nivre’s parser (Nivre, 2003) that first identifies the parse actions and then labels the dependency arcs. These two steps are implemented as SVM classifiers using LIBSVM. Features take into account the static context as well as relations dynamically built during parsing.

We experimented two main additions to our implementation of Nivre’s parser: N-best search and bidirectional parsing. We trained the parser in both left-right and right-left directions and we combined the results. To construct a single-head, rooted, and cycle-free tree, we applied the Chu-Liu/Edmonds optimization algorithm. We ran the same algorithm with the same parameters on all the languages. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Natural language processing, dependency parsing
host publication
Proceedings of the Tenth Conference on Computational Natural Language Learning (CONLL-X)
editor
Màrquez, Lluís and Klein, Dan
pages
5 pages
publisher
Association for Computational Linguistics
conference name
Tenth Conference on Computational Natural Language Learning (CONLL-X)
conference location
New York, United States
conference dates
2006-06-08 - 2006-06-09
external identifiers
  • scopus:85088750513
language
English
LU publication?
yes
id
f61cff3a-d292-4b14-82d9-10ad2f7d19bc (old id 632038)
date added to LUP
2016-04-04 10:18:00
date last changed
2022-02-21 02:56:24
@inproceedings{f61cff3a-d292-4b14-82d9-10ad2f7d19bc,
  abstract     = {{In this paper, we describe a system for the CoNLL-X shared task of multilingual dependency parsing. It uses a baseline Nivre’s parser (Nivre, 2003) that first identifies the parse actions and then labels the dependency arcs. These two steps are implemented as SVM classifiers using LIBSVM. Features take into account the static context as well as relations dynamically built during parsing.<br/><br>
We experimented two main additions to our implementation of Nivre’s parser: N-best search and bidirectional parsing. We trained the parser in both left-right and right-left directions and we combined the results. To construct a single-head, rooted, and cycle-free tree, we applied the Chu-Liu/Edmonds optimization algorithm. We ran the same algorithm with the same parameters on all the languages.}},
  author       = {{Johansson, Richard and Nugues, Pierre}},
  booktitle    = {{Proceedings of the Tenth Conference on Computational Natural Language Learning (CONLL-X)}},
  editor       = {{Màrquez, Lluís and Klein, Dan}},
  keywords     = {{Natural language processing; dependency parsing}},
  language     = {{eng}},
  pages        = {{206--210}},
  publisher    = {{Association for Computational Linguistics}},
  title        = {{Investigating multilingual dependency parsing}},
  url          = {{https://lup.lub.lu.se/search/files/5508036/1058046.pdf}},
  year         = {{2006}},
}