Learning reliable information for dependency parsing adaptation

Authors:
Wenliang Chen;Youzheng Wu;Hitoshi Isahara
Affiliations:
National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan;National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan;National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan
Venue:
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Year:
2008

Citing 4
Cited 2

TnT: a statistical part-of-speech tagger

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Reranking and self-training for parser adaptation

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Multilingual dependency analysis with a two-stage discriminative parser

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

Automatic selection of high quality parses created by a fully unsupervised parser

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning
Correcting dependency annotation errors

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we focus on the adaptation problem that has a large labeled data in the source domain and a large but unlabeled data in the target domain. Our aim is to learn reliable information from unlabeled target domain data for dependency parsing adaptation. Current state-of-the-art statistical parsers perform much better for shorter dependencies than for longer ones. Thus we propose an adaptation approach by learning reliable information on shorter dependencies in an unlabeled target data to help parse longer distance words. The unlabeled data is parsed by a dependency parser trained on labeled source domain data. The experimental results indicate that our proposed approach outperforms the baseline system, and is better than current state-of-the-art adaptation techniques.