Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data

Xinyu Wang, Yong Jiang, Kewei Tu


Abstract
This paper presents the system used in our submission to the IWPT 2020 Shared Task. Our system is a graph-based parser with second-order inference. For the low-resource Tamil corpora, we specially mixed the training data of Tamil with other languages and significantly improved the performance of Tamil. Due to our misunderstanding of the submission requirements, we submitted graphs that are not connected, which makes our system only rank 6th over 10 teams. However, after we fixed this problem, our system is 0.6 ELAS higher than the team that ranked 1st in the official results.
Anthology ID:
2020.iwpt-1.22
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:
215–220
Language:
URL:
https://aclanthology.org/2020.iwpt-1.22
DOI:
10.18653/v1/2020.iwpt-1.22
Bibkey:
Cite (ACL):
Xinyu Wang, Yong Jiang, and Kewei Tu. 2020. Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 215–220, Online. Association for Computational Linguistics.
Cite (Informal):
Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data (Wang et al., IWPT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwpt-1.22.pdf
Video:
 http://slideslive.com/38929689
Code
 Alibaba-NLP/MultilangStructureKD
Data
Universal Dependencies