Pseudo-projective dependency parsing
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
LIBLINEAR: A Library for Large Linear Classification
The Journal of Machine Learning Research
CoNLL-X shared task on multilingual dependency parsing
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Labeled pseudo-projective dependency parsing with support vector machines
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Transition-based parsing of the Chinese treebank using a global discriminative model
IWPT '09 Proceedings of the 11th International Conference on Parsing Technologies
MaltOptimizer: an optimization tool for MaltParser
EACL '12 Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics
| Hi-index | 0.00 |
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.