One-Shot Prompt for Language Variety Identification

Nat Gillin


Abstract
We present a one-shot prompting approach to multi-class classification for similar language identification with off-the-shelf pre-trained large language model that is not particularly trained or tuned for the language identification task. Without post-training or fine-tuning the model, we simply include one example per class when prompting the model and surprisingly the model to generate the language andlocale labels accordingly.
Anthology ID:
2024.vardial-1.20
Volume:
Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Yves Scherrer, Tommi Jauhiainen, Nikola Ljubešić, Marcos Zampieri, Preslav Nakov, Jörg Tiedemann
Venues:
VarDial | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
230–234
Language:
URL:
https://aclanthology.org/2024.vardial-1.20
DOI:
10.18653/v1/2024.vardial-1.20
Bibkey:
Cite (ACL):
Nat Gillin. 2024. One-Shot Prompt for Language Variety Identification. In Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024), pages 230–234, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
One-Shot Prompt for Language Variety Identification (Gillin, VarDial-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.vardial-1.20.pdf
Supplementary material:
 2024.vardial-1.20.SupplementaryMaterial.txt