Multi-Model and Crosslingual Dependency Analysis

Johannes Heinecke, Munshi Asadullah


Abstract
This paper describes the system of the Team Orange-Deskiñ, used for the CoNLL 2017 UD Shared Task in Multilingual Dependency Parsing. We based our approach on an existing open source tool (BistParser), which we modified in order to produce the required output. Additionally we added a kind of pseudo-projectivisation. This was needed since some of the task’s languages have a high percentage of non-projective dependency trees. In most cases we also employed word embeddings. For the 4 surprise languages, the data provided seemed too little to train on. Thus we decided to use the training data of typologically close languages instead. Our system achieved a macro-averaged LAS of 68.61% (10th in the overall ranking) which improved to 69.38% after bug fixes.
Anthology ID:
K17-3011
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:
111–118
Language:
URL:
https://aclanthology.org/K17-3011
DOI:
10.18653/v1/K17-3011
Bibkey:
Cite (ACL):
Johannes Heinecke and Munshi Asadullah. 2017. Multi-Model and Crosslingual Dependency Analysis. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 111–118, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Multi-Model and Crosslingual Dependency Analysis (Heinecke & Asadullah, CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3011.pdf
Poster:
 K17-3011.Poster.pdf
Data
Universal Dependencies