Text2Sentiment is a flexible, reusable framework for building Text Classification models. This repository is specifically designed for PyTorch and can be applied to numerous different datasets.
Inspired by bentrevett's PyTorch Sentiment Analysis and the PyTorch Documentation Examples, this project was created to modernize older resources and replace the usage of legacy packages.
The initial implementation performs Sentiment Analysis on the TorchText IMDB dataset, but the architecture of the codebase allows for easy adaptation to other text datasets.
The project heavily relies on:
- Python
- PyTorch
- Ubuntu
Coming soon...
A detailed guide on how to use this project will be published shortly. The guide will contain information about how to adapt the codebase to work with various text datasets.
Contributions, issues and feature requests are welcome. Feel free to check issues page if you want to contribute.
This project is MIT licensed.