Extractive text summarization using genetic algorithms.
pip install requirements.txt
This splits the corpus in the stories folder into a body (the actual article) and highlights (the summary). Does not split dataset into training and testing.
cd src
python dataset.py
The program assumes that the dataset is split into training and testing in the following manner. There is no script included for automatic splitting.
GA-Text-Summarization\src\dataset\train\body\sample.txt
GA-Text-Summarization\src\dataset\train\highlights\sample.txt
GA-Text-Summarization\src\dataset\test\body\sample.txt
GA-Text-Summarization\src\dataset\test\highlights\sample.txt
cd src
python main.py
cd src
python test.py