Single document extractive text summarization using cuckoo search algorithm

Abstract

In today’s world, the rapid growth of text data on web and online resources makes a challenging problem for the human beings to get the essential information. Finding such information can only be feasible by summarizing the text, known as Text summarization (TS). TS is the process of compressing the original text document without losing the core contents. Hence the most conventional and tricky method for summarization is to fetch the most informative or representative sentences from the original input document which is well-known as Extractive Text Summarization. It has the potential to obtain the valuable information in the shortest period of time. In this paper, three different nature-inspired algorithms such as Cuckoo search algorithm (CS), Firefly algorithm (FF) & Flower pollination algorithm (FP) are used to generate the summary for a document. The implementation is done over DUC 2003 dataset. However, the CS algorithm-based model is showing significantly better result than the other two models for this problem.

Subject Classification:

• 68T50 Natural language processing

Keywords:

• Text summarization
• Cuckoo search algorithm
• Firefly algorithm
• Flower pollination algorithm