Semantic Abstract Generator

This repository contains the source code for a study on generating abstracts for given texts using a fine-tuned T5-base transformer model.

Dataset

The dataset used in this study can be found at Dataset.

The subset of the dataset i used for training the model can be found at Dataset.

To run the code in this repository, you will need to have Python 3.6 or later installed, along with the following libraries:

The model achieved a precision of 0.5, a recall of 0.6, and an f1 score of 0.6 on the test dataset.

Average semantic similarity: 0.268

Average cosine similarity: 0.451

The Report for the particular project can be found at Report

This project is licensed under the MIT License. See the LICENSE file for more information.

Name		Name	Last commit message	Last commit date
Latest commit History 11 Commits
Dataset.ipynb		Dataset.ipynb
Information_Retrival_Report.pdf		Information_Retrival_Report.pdf
README.md		README.md
T5_News__summary_.ipynb		T5_News__summary_.ipynb