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
- 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)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/K18-2025.pdf