Cross-Dialectal Transfer and Zero-Shot Learning for Armenian Varieties: A Comparative Analysis of RNNs, Transformers and LLMs

Chahan Vidal-Gorène, Nadi Tomeh, Victoria Khurshudyan


Abstract
This paper evaluates lemmatization, POS-tagging, and morphological analysis for four Armenian varieties: Classical Armenian, Modern Eastern Armenian, Modern Western Armenian, and the under-documented Getashen dialect. It compares traditional RNN models, multilingual models like mDeBERTa, and large language models (ChatGPT) using supervised, transfer learning, and zero/few-shot learning approaches. The study finds that RNN models are particularly strong in POS-tagging, while large language models demonstrate high adaptability, especially in handling previously unseen dialect variations. The research highlights the value of cross-variational and in-context learning for enhancing NLP performance in low-resource languages, offering crucial insights into model transferability and supporting the preservation of endangered dialects.
Anthology ID:
2024.nlp4dh-1.42
Volume:
Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
Month:
November
Year:
2024
Address:
Miami, USA
Editors:
Mika Hämäläinen, Emily Öhman, So Miyagawa, Khalid Alnajjar, Yuri Bizzoni
Venue:
NLP4DH
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
438–449
Language:
URL:
https://aclanthology.org/2024.nlp4dh-1.42
DOI:
Bibkey:
Cite (ACL):
Chahan Vidal-Gorène, Nadi Tomeh, and Victoria Khurshudyan. 2024. Cross-Dialectal Transfer and Zero-Shot Learning for Armenian Varieties: A Comparative Analysis of RNNs, Transformers and LLMs. In Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities, pages 438–449, Miami, USA. Association for Computational Linguistics.
Cite (Informal):
Cross-Dialectal Transfer and Zero-Shot Learning for Armenian Varieties: A Comparative Analysis of RNNs, Transformers and LLMs (Vidal-Gorène et al., NLP4DH 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nlp4dh-1.42.pdf