A Fast and Lightweight System for Multilingual Dependency Parsing

Tao Ji, Yuanbin Wu, Man Lan


Abstract
We present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33%.
Anthology ID:
K17-3025
Volume:
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Jan Hajič, Dan Zeman
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
237–242
Language:
URL:
https://aclanthology.org/K17-3025
DOI:
10.18653/v1/K17-3025
Bibkey:
Cite (ACL):
Tao Ji, Yuanbin Wu, and Man Lan. 2017. A Fast and Lightweight System for Multilingual Dependency Parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 237–242, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
A Fast and Lightweight System for Multilingual Dependency Parsing (Ji et al., CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3025.pdf