These projects focus on natural language processing for Armenian, including parsing, embeddings, punctuation, loanword detection, tokenizer adaptation, and large language model evaluation.
This repository contains NLP parsing models (likely dependency parsers and/or part-of-speech taggers) specifically tr...
This repository contains the code and data pipelines for a bachelor thesis project on Armenian NLP, specifically focu...
A research project exploring machine learning approaches for detecting loanwords in Armenian and predicting their lan...
A complete pipeline for training Word2Vec embeddings on Armenian text, including data preprocessing, model training w...
A capstone project evaluating GPT-3.5-Turbo's performance on Armenian language tasks, including extractive QA, multip...
A research project focused on improving NLP for the low-resource Armenian language by analyzing tokenizer inefficienc...