Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings

Xinyu Wang, Zixia Jia, Yong Jiang, Kewei Tu


Abstract
This paper describe the system used in our submission to the IWPT 2021 Shared Task. Our system is a graph-based parser with the technique of Automated Concatenation of Embeddings (ACE). Because recent work found that better word representations can be obtained by concatenating different types of embeddings, we use ACE to automatically find the better concatenation of embeddings for the task of enhanced universal dependencies. According to official results averaged on 17 languages, our system rank 2nd over 9 teams.
Anthology ID:
2021.iwpt-1.20
Volume:
Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Stephan Oepen, Kenji Sagae, Reut Tsarfaty, Gosse Bouma, Djamé Seddah, Daniel Zeman
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
189–195
Language:
URL:
https://aclanthology.org/2021.iwpt-1.20
DOI:
10.18653/v1/2021.iwpt-1.20
Bibkey:
Cite (ACL):
Xinyu Wang, Zixia Jia, Yong Jiang, and Kewei Tu. 2021. Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings. In Proceedings of the 17th International Conference on Parsing Technologies and the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (IWPT 2021), pages 189–195, Online. Association for Computational Linguistics.
Cite (Informal):
Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings (Wang et al., IWPT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.iwpt-1.20.pdf
Video:
 https://aclanthology.org/2021.iwpt-1.20.mp4
Data
Universal Dependencies