Corpus Selection Approaches for Multilingual Parsing from Raw Text to Universal Dependencies

Ryan Hornby, Clark Taylor, Jungyeul Park


Abstract
This paper describes UALing’s approach to the CoNLL 2017 UD Shared Task using corpus selection techniques to reduce training data size. The methodology is simple: we use similarity measures to select a corpus from available training data (even from multiple corpora for surprise languages) and use the resulting corpus to complete the parsing task. The training and parsing is done with the baseline UDPipe system (Straka et al., 2016). While our approach reduces the size of training data significantly, it retains performance within 0.5% of the baseline system. Due to the reduction in training data size, our system performs faster than the naïve, complete corpus method. Specifically, our system runs in less than 10 minutes, ranking it among the fastest entries for this task. Our system is available at https://github.com/CoNLL-UD-2017/UALING.
Anthology ID:
K17-3021
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:
198–206
Language:
URL:
https://aclanthology.org/K17-3021
DOI:
10.18653/v1/K17-3021
Bibkey:
Cite (ACL):
Ryan Hornby, Clark Taylor, and Jungyeul Park. 2017. Corpus Selection Approaches for Multilingual Parsing from Raw Text to Universal Dependencies. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 198–206, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Corpus Selection Approaches for Multilingual Parsing from Raw Text to Universal Dependencies (Hornby et al., CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3021.pdf
Code
 CoNLL-UD-2017/UALING