Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages

Xiang Yu, Ngoc Thang Vu


Abstract
We present a transition-based dependency parser that uses a convolutional neural network to compose word representations from characters. The character composition model shows great improvement over the word-lookup model, especially for parsing agglutinative languages. These improvements are even better than using pre-trained word embeddings from extra data. On the SPMRL data sets, our system outperforms the previous best greedy parser (Ballesteros et. al, 2015) by a margin of 3% on average.
Anthology ID:
P17-2106
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
672–678
Language:
URL:
https://aclanthology.org/P17-2106
DOI:
10.18653/v1/P17-2106
Bibkey:
Cite (ACL):
Xiang Yu and Ngoc Thang Vu. 2017. Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 672–678, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages (Yu & Vu, ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-2106.pdf