Amen-Zelealem/Amharic-NER-LLM-EcomInsightsEthiopia
Domaine:
natural language processingType de record:
project
Créateur:
Ame
Hôte:
A repository dedicated to extracting insights and data from Telegram channels to optimize the e-commerce landscape in Ethiopia.
# 🛒 **Amharic-NER-LLM-EcomInsightsEthiopia**
A comprehensive repository dedicated to **extracting insights** and **data** from Telegram channels, aimed at **optimizing** the e-commerce landscape in Ethiopia.
### 🔍 **Overview**
This repository serves as a framework for leveraging **Named Entity Recognition (NER)** in the Amharic language, specifically tailored for e-commerce applications.
## Selected Channels
The following Ethiopian-based Telegram e-commerce channels have been selected for data ingestion:
- **@ethio_brand_collection**
## 📂 **Project Structure**
```
+---.github
| └── workflows
| └── blank.yml
+---.vscode
| └── settings.json
+---notebooks
| ├── data_processing.ipynb
| ├── fine_tunning.ipynb
| ├── init.ipynb
| └── README.md
+---scripts
| ├── data_labeler.py
| ├── data_preprocessor.py
| ├── data_scrapper.py
| ├── init.py
| └── README.md
+---src
| └── README.md
| └── init.py
+---tests
| ├── README.md
| └── init.py
| └── test_data_labeler.py
| └── test_data_preprocessing.py
| └──test_data_scrapper.py
| ├── .gitignore
| ├── labeled_data_conll.conll
| ├── README.md
| └── requirements.txt
```
## 🛠️ Tools and Libraries
- **Python**: The primary programming language used for the implementation.
- **Telethon**: A Python library for interacting with Telegram’s API to scrape messages.
- **Pandas**: For data manipulation and storage in structured formats.
- **NLTK or SpaCy**: For text preprocessing and tokenization specific to Amharic linguistic features.
## 🚀 Installation Instructions
To run the project locally, follow these steps:
Clone the Repository:
`git clone github.com`
`cd Amharic-NER-LLM-EcomInsightsEthiopia`
Set up the Virtual Environment:
`python3 -m venv .venv`
`source .venv/bin/activate # For Windows: .venv\Scripts\activate`
Install Dependencies:
`pip install -r requirements.txt`
## Models Evaluated 🤖
1. **XLM-Roberta**
- Pre-trained on 100 languages, including Amharic. 🌐
- E …