DMCA
2008. A tale of two parsers: Investigating and combining graph-based and transition-based dependency parsing
Cached
Download Links
| Venue: | In Proceedings of EMNLP 2008 |
| Citations: | 90 - 12 self |
BibTeX
@INPROCEEDINGS{Zhang_2008.a,
author = {Yue Zhang and Stephen Clark},
title = {2008. A tale of two parsers: Investigating and combining graph-based and transition-based dependency parsing},
booktitle = {In Proceedings of EMNLP 2008},
year = {},
pages = {562--571}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Graph-based and transition-based approaches to dependency parsing adopt very different views of the problem, each view having its own strengths and limitations. We study both approaches under the framework of beamsearch. By developing a graph-based and a transition-based dependency parser, we show that a beam-search decoder is a competitive choice for both methods. More importantly, we propose a beam-search-based parser that combines both graph-based and transitionbased parsing into a single system for training and decoding, showing that it outperforms both the pure graph-based and the pure transition-based parsers. Testing on the English and Chinese Penn Treebank data, the combined system gave state-of-the-art accuracies
Keyphrases
transition-based dependency single system beam-search decoder competitive choice pure transition-based parser different view transition-based dependency parser transitionbased parsing transition-based approach state-of-the-art accuracy chinese penn treebank data combined system beam-search-based parser
