AntNLP at CoNLL 2018 Shared Task: A Graph-Based Parser for Universal Dependency Parsing

Tao Ji, Yufang Liu, Yijun Wang, Yuanbin Wu, Man Lan


Abstract
We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).
Anthology ID:
K18-2025
Volume:
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
October
Year:
2018
Address:
Brussels, Belgium
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
248–255
Language:
URL:
https://aclanthology.org/K18-2025
DOI:
10.18653/v1/K18-2025
Bibkey:
Cite (ACL):
Tao Ji, Yufang Liu, Yijun Wang, Yuanbin Wu, and Man Lan. 2018. AntNLP at CoNLL 2018 Shared Task: A Graph-Based Parser for Universal Dependency Parsing. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 248–255, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
AntNLP at CoNLL 2018 Shared Task: A Graph-Based Parser for Universal Dependency Parsing (Ji et al., CoNLL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/K18-2025.pdf