Multi-Document Summarization using Discrete Bat Optimization

Abstract

With the World Wide Web, we now have a wide range of data that was previously unavailable. Therefore, it has become a complex problem to find useful information in large datasets. In recent years, text summarization has emerged as a viable option for mining relevant data from massive collections of texts. We may classify summarizing as either "single document" or "multi document" depending on how many source documents we are working with. Finding an accurate summary from a collection of documents is more difficult for researchers than doing it from a single document. For this reason, this research proposes a Discrete Bat algorithm Optimization based multi document summarizer (DBAT-MDS) to tackle the issue of multi document summarizing. Comparisons are made between the proposed DBAT-MDS based model and three different summarization algorithms that take their inspiration from the natural world. All methods are evaluated in relation to the benchmark Document Understanding Conference (DUC) datasets using a variety of criteria, such as the ROUGE score and the F score. Compared to the other summarizers used in the experiment, the suggested method performs much better.