Efficient EUD Parsing

Mathieu Dehouck, Mark Anderson, Carlos Gómez-Rodríguez


Abstract
We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2020. We engaged with the task by focusing on efficiency. For this we considered training costs and inference efficiency. Our models are a combination of distilled neural dependency parsers and a rule-based system that projects UD trees into EUD graphs. We obtained an average ELAS of 74.04 for our official submission, ranking 4th overall.
Anthology ID:
2020.iwpt-1.20
Volume:
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
Month:
July
Year:
2020
Address:
Online
Editors:
Gosse Bouma, Yuji Matsumoto, Stephan Oepen, Kenji Sagae, Djamé Seddah, Weiwei Sun, Anders Søgaard, Reut Tsarfaty, Dan Zeman
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
192–205
Language:
URL:
https://aclanthology.org/2020.iwpt-1.20
DOI:
10.18653/v1/2020.iwpt-1.20
Bibkey:
Cite (ACL):
Mathieu Dehouck, Mark Anderson, and Carlos Gómez-Rodríguez. 2020. Efficient EUD Parsing. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 192–205, Online. Association for Computational Linguistics.
Cite (Informal):
Efficient EUD Parsing (Dehouck et al., IWPT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwpt-1.20.pdf
Video:
 http://slideslive.com/38929687