These projects are all focused on developing and evaluating natural language processing tools, such as embedding models, recommendation systems, and RAG pipelines, specifically for the Armenian language.
ArmBench-TextEmbed is a specialized Python benchmark for evaluating the performance of text embedding models on the A...
This repository presents a benchmark for evaluating multilingual sentence embedding models on a real-world task: cros...
A Retrieval-Augmented Generation (RAG) system designed to answer questions about Armenian Labor Law in Armenian. It i...
A Master's thesis project implementing a full Retrieval-Augmented Generation (RAG) pipeline for querying Armenian ban...
A book recommendation system project using Armenian user data, implementing both collaborative filtering and content-...