MTSQIGA: A Novel Extractive Multi-document Text Summarization System using Quantum-Inspired Genetic Algorithm

Code repository for the manuscript A Novel Extractive Multi-document Text Summarization System using Quantum-Inspired Genetic Algorithm.

Authors: Mohammad Mojrian and Seyed Abolghasem Mirroshandel (University of Guilan).

Contact: [email protected]

Prerequisites

The code is developed with python 3.6 and uses NLTK module for preprocessing step. For more requirements, please check requirements.txt.

• Python >= 3.6
• NLTK

Installing NLTK data

We have used two corpora of NLTK in this code. To install them you should first install required packages:

make setup

Then you should install stopwords and punkt corpora of NLTK. To install them:

import nltk
nltk.download('stopwords')
nltk.download('punkt')

Run the main algorithm

To run the summarizer on a dataset, use command:

make serve

Evaluation with ROUGE

The evaluation directory contains some code to evaluate the generated summary with ROUGE toolkit and get a CSV output from the results. It includes codes to organize a directory based on ROUGE format as well as providing tools to utilize ROUGE on the generated summaries in terms of ROUGE-1, ROUGE-2, and ROUGE-SU4.