Advanced

Automatic discovery of feature sets for dependency parsing

Nilsson, Peter and Nugues, Pierre LU (2010) In Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010) p.824-832
Abstract
This paper describes a search procedure to discover optimal feature sets for dependency parsers. The search applies to the shift–reduce algorithm and the feature sets are extracted from the parser configuration. The initial feature is limited to the first word in the input queue. Then, the procedure uses a set of rules founded on the assumption that topological neighbors of significant features in the dependency graph may also have a significant contribution. The search can be fully automated and the level of greediness adjusted with the number of features examined at each iteration of the discovery procedure. Using our automated feature discovery on two corpora, the Swedish corpus in CoNLL-X and the English corpus in CoNLL 2008, and a... (More)
This paper describes a search procedure to discover optimal feature sets for dependency parsers. The search applies to the shift–reduce algorithm and the feature sets are extracted from the parser configuration. The initial feature is limited to the first word in the input queue. Then, the procedure uses a set of rules founded on the assumption that topological neighbors of significant features in the dependency graph may also have a significant contribution. The search can be fully automated and the level of greediness adjusted with the number of features examined at each iteration of the discovery procedure. Using our automated feature discovery on two corpora, the Swedish corpus in CoNLL-X and the English corpus in CoNLL 2008, and a single parser system, we could reach results comparable or better than the best scores reported in these evaluations. The CoNLL 2008 test set contains, in addition to a Wall Street Journal (WSJ) section, an out-of-domain sample from the Brown corpus. With sets of 15 features, we obtained a labeled attachment score of 84.21 for Swedish, 88.11 on the WSJ test set, and 81.33 on the Brown test set. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010)
pages
824 - 832
external identifiers
  • Scopus:80053412836
language
English
LU publication?
yes
id
67a19e11-9947-4c31-84f1-6c5fd8949bd2 (old id 1668787)
alternative location
http://www.aclweb.org/anthology/C/C10/C10-1093.pdf
date added to LUP
2010-12-10 12:11:05
date last changed
2017-02-26 04:34:17
@inproceedings{67a19e11-9947-4c31-84f1-6c5fd8949bd2,
  abstract     = {This paper describes a search procedure to discover optimal feature sets for dependency parsers. The search applies to the shift–reduce algorithm and the feature sets are extracted from the parser configuration. The initial feature is limited to the first word in the input queue. Then, the procedure uses a set of rules founded on the assumption that topological neighbors of significant features in the dependency graph may also have a significant contribution. The search can be fully automated and the level of greediness adjusted with the number of features examined at each iteration of the discovery procedure. Using our automated feature discovery on two corpora, the Swedish corpus in CoNLL-X and the English corpus in CoNLL 2008, and a single parser system, we could reach results comparable or better than the best scores reported in these evaluations. The CoNLL 2008 test set contains, in addition to a Wall Street Journal (WSJ) section, an out-of-domain sample from the Brown corpus. With sets of 15 features, we obtained a labeled attachment score of 84.21 for Swedish, 88.11 on the WSJ test set, and 81.33 on the Brown test set.},
  author       = {Nilsson, Peter and Nugues, Pierre},
  booktitle    = {Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010)},
  language     = {eng},
  pages        = {824--832},
  title        = {Automatic discovery of feature sets for dependency parsing},
  year         = {2010},
}