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

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.