Multilingual Universal Dependency Parsing from Raw Text with Low-Resource Language Enhancement

Yingting Wu, Hai Zhao, Jia-Jun Tong


Abstract
This paper describes the system of our team Phoenix for participating CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Given the annotated gold standard data in CoNLL-U format, we train the tokenizer, tagger and parser separately for each treebank based on an open source pipeline tool UDPipe. Our system reads the plain texts for input, performs the pre-processing steps (tokenization, lemmas, morphology) and finally outputs the syntactic dependencies. For the low-resource languages with no training data, we use cross-lingual techniques to build models with some close languages instead. In the official evaluation, our system achieves the macro-averaged scores of 65.61%, 52.26%, 55.71% for LAS, MLAS and BLEX respectively.
Anthology ID:
K18-2007
Volume:
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Daniel Zeman, Jan Hajič
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
74–80
Language:
URL:
https://aclanthology.org/K18-2007
DOI:
10.18653/v1/K18-2007
Bibkey:
Cite (ACL):
Yingting Wu, Hai Zhao, and Jia-Jun Tong. 2018. Multilingual Universal Dependency Parsing from Raw Text with Low-Resource Language Enhancement. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 74–80, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Multilingual Universal Dependency Parsing from Raw Text with Low-Resource Language Enhancement (Wu et al., CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-2007.pdf
Data
Universal Dependencies