A System for Multilingual Dependency Parsing based on Bidirectional LSTM Feature Representations

KyungTae Lim, Thierry Poibeau


Abstract
In this paper, we present our multilingual dependency parser developed for the CoNLL 2017 UD Shared Task dealing with “Multilingual Parsing from Raw Text to Universal Dependencies”. Our parser extends the monolingual BIST-parser as a multi-source multilingual trainable parser. Thanks to multilingual word embeddings and one hot encodings for languages, our system can use both monolingual and multi-source training. We trained 69 monolingual language models and 13 multilingual models for the shared task. Our multilingual approach making use of different resources yield better results than the monolingual approach for 11 languages. Our system ranked 5 th and achieved 70.93 overall LAS score over the 81 test corpora (macro-averaged LAS F1 score).
Anthology ID:
K17-3006
Volume:
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
63–70
Language:
URL:
https://aclanthology.org/K17-3006
DOI:
10.18653/v1/K17-3006
Bibkey:
Cite (ACL):
KyungTae Lim and Thierry Poibeau. 2017. A System for Multilingual Dependency Parsing based on Bidirectional LSTM Feature Representations. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 63–70, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
A System for Multilingual Dependency Parsing based on Bidirectional LSTM Feature Representations (Lim & Poibeau, CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3006.pdf