Abstract
In this work, we focus on low-resource dependency parsing for multiple languages. Several strategies are tailored to enhance performance in low-resource scenarios. While these are well-known to the community, it is not trivial to select the best-performing combination of these strategies for a low-resource language that we are interested in, and not much attention has been given to measuring the efficacy of these strategies. We experiment with 5 low-resource strategies for our ensembled approach on 7 Universal Dependency (UD) low-resource languages. Our exhaustive experimentation on these languages supports the effective improvements for languages not covered in pretrained models. We show a successful application of the ensembled system on a truly low-resource language Sanskrit. The code and data are available at: https://github.com/Jivnesh/SanDP- Anthology ID:
- 2023.eacl-main.158
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2164–2171
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.158
- DOI:
- 10.18653/v1/2023.eacl-main.158
- Cite (ACL):
- Jivnesh Sandhan, Laxmidhar Behera, and Pawan Goyal. 2023. Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2164–2171, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing (Sandhan et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.eacl-main.158.pdf