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.
Cite
CITATION STYLE
Choudhary, C., & O’Riordan, C. (2021). Improving the performance of UDify with Linguistic Typology Knowledge. In SIGTYP 2021 - 3rd Workshop on Research in Computational Typology and Multilingual NLP, Proceedings of the Workshop (pp. 38–60). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.sigtyp-1.5
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
