Improving the Performance of UDify with Linguistic Typology Knowledge

Chinmay Choudhary


Abstract
UDify is the state-of-the-art language-agnostic dependency parser which is trained on a polyglot corpus of 75 languages. This multilingual modeling enables the model to generalize over unknown/lesser-known languages, thus leading to improved performance on low-resource languages. In this work we used linguistic typology knowledge available in URIEL database, to improve the cross-lingual transferring ability of UDify even further.
Anthology ID:
2021.sigtyp-1.5
Volume:
Proceedings of the Third Workshop on Computational Typology and Multilingual NLP
Month:
June
Year:
2021
Address:
Online
Editors:
Ekaterina Vylomova, Elizabeth Salesky, Sabrina Mielke, Gabriella Lapesa, Ritesh Kumar, Harald Hammarström, Ivan Vulić, Anna Korhonen, Roi Reichart, Edoardo Maria Ponti, Ryan Cotterell
Venue:
SIGTYP
SIG:
SIGTYP
Publisher:
Association for Computational Linguistics
Note:
Pages:
38–60
Language:
URL:
https://aclanthology.org/2021.sigtyp-1.5
DOI:
10.18653/v1/2021.sigtyp-1.5
Bibkey:
Cite (ACL):
Chinmay Choudhary. 2021. Improving the Performance of UDify with Linguistic Typology Knowledge. In Proceedings of the Third Workshop on Computational Typology and Multilingual NLP, pages 38–60, Online. Association for Computational Linguistics.
Cite (Informal):
Improving the Performance of UDify with Linguistic Typology Knowledge (Choudhary, SIGTYP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigtyp-1.5.pdf