Emanzaddu/NER-for-Gamo-Language

Deep learning-based Named Entity Recognition (NER) model for the low-resource Gamo language. Natural Language Processing (NLP) resources for low-resource Ethiopian languages remain scarce. This thesis presents a Named Entity Recognition (NER) framework tailored specifically for the Gamo language using deep learning techniques. By leveraging neural architectures to extract key entities—such as names, locations, and organizations—from unstructured Gamo text, this work addresses key linguistic challenges and establishes a baseline for future NLP and information extraction research in low-resource settings. Key Highlights (Quick Bullet Points for the README) - Focus: Named Entity Recognition (NER) for the Gamo language. - Approach: Deep learning architectures optimized for low-resource NLP. - Goal: Automated identification of entities (Persons, Locations, Organizations, etc.) in unstructured text.