Two-stage Pipeline for Multilingual Dialect Detection
Published in EACL VarDial Workshop, 2023
Recommended citation: Vaidya, A. and Kane, A., 2023. Two-stage Pipeline for Multilingual Dialect Detection. arXiv preprint arXiv:2303.03487. https://arxiv.org/pdf/2303.03487.pdf
Dialect Identification is a crucial task for localizing various Large Language Models. This paper outlines our approach to the VarDial 2023 shared task. Here we have to identify three or two dialects from three languages each which results in a 9-way classification for Track-1 and 6-way classification for Track-2 respectively. Our proposed approach consists of a two-stage system and outperforms other participants’ systems and previous works in this domain. We achieve a score of 58.54% for Track-1 and 85.61% for Track-2. Our codebase is available publicly here.
If you find our paper useful in your research, please consider citing:
@misc{vaidya2023twostage,
title={Two-stage Pipeline for Multilingual Dialect Detection},
author={Ankit Vaidya and Aditya Kane},
year={2023},
eprint={2303.03487},
archivePrefix={arXiv},
primaryClass={cs.CL}
}