nebiyu-getachew/Amharic_Entity_Master

# EthioMart Telegram E-commerce Hub - Amharic Named Entity Recognition (NER) ## Overview EthioMart aims to become the primary hub for all Telegram-based e-commerce activities in Ethiopia. With the growing use of Telegram for business, many independent e-commerce channels have emerged, presenting challenges for both vendors and customers. EthioMart's goal is to create a centralized platform to consolidate real-time data from these multiple channels, providing a seamless experience for product discovery and interaction. This project focuses on fine-tuning a large language model (LLM) for Amharic Named Entity Recognition (NER). The system will extract key business entities such as product names, prices, and locations from text, images, and documents shared across Telegram e-commerce channels. The extracted data will populate EthioMart’s centralized database, making it a comprehensive e-commerce hub. ## Key Objectives - Real-time data extraction from Telegram channels - Fine-tuning LLMs to extract entities such as product names, prices, and locations - Creating a unified, searchable database for customers ## Possible Entities - **Product Names** or Types - **Materials** or Ingredients - **Location Mentions** - **Monetary Values** or Prices ## Data - **Sources**: Messages and data from Ethiopian-based Telegram e-commerce channels t.me - **Types**: - Text (Amharic language messages) - Images (Product images, marketing materials) ## Technologies and Tools - **Text Processing**: Handling Amharic text, tokenization, and preprocessing techniques. - **LLM Fine-tuning**: Adapting large language models for Amharic NER tasks. - **Model Evaluation**: Using metrics such as F1-score, precision, and recall to compare model performance. - **Model Interpretability**: Using tools like SHAP and LIME to explain model predictions. ## Learning Outcomes By the end of the project, the following outcomes are expected: - A fully functional pipeline for extracting …