The paper explores the development of Automatic Speech Recognition (ASR) models for Armenian, by using data from two standard dialects (Eastern Armenian and Western Armenian). The goal is to develop a joint bi-variational model. We achieve state-of-the-art results. Results from our ASR experiments demonstrate the impact of dataset selection and data volume on model performance. The study reveals limited transferability between dialects, although integrating datasets from both dialects enhances overall performance. The paper underscores the importance of dataset diversity and volume in ASR model training for under-resourced languages like Armenian.

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.

Eastern Armenian National Corpus (EANC) is a comprehensive corpus of Modern Eastern Armenian with about 110 million tokens, covering written and oral discourses from the mid-19th century to the present. The corpus is provided with morphological, semantic and metatext annotation, as well as English translations. EANC is open access and available at www.eanc.net.

Armenian is a language with significant variation and unevenly distributed NLP resources for different varieties. An attempt is made to process an RNN model for morphological annotation on the basis of different Armenian data (provided or not with morphologically annotated corpora), and to compare the annotation results of RNN and rule-based models. Different tests were carried out to evaluate the reuse of an unspecialized model of lemmatization and POS-tagging for under-resourced language varieties. The research focused on three dialects and further extended to Western Armenian with a mean accuracy of 94,00 % in lemmatization and 97,02% in POS-tagging, as well as a possible reusability of models to cover different other Armenian varieties. Interestingly, the comparison of an RNN model trained on Eastern Armenian with the Eastern Armenian National Corpus rule-based model applied to Western Armenian showed an enhancement of 19% in parsing. This model covers 88,79% of a short heterogeneous dataset in Western Armenian, and could be a baseline for a massive corpus annotation in that standard. It is argued that an RNN-based model can be a valid alternative to a rule-based one giving consideration to such factors as time-consumption, reusability for different varieties of a target language and significant qualitative results in morphological annotation.