ENHANCING ABSTRACTIVE TEXT SUMMARIZATION THROUGH FEATURE FUSION-BASED NEURAL NETWORK MODEL

Text summarization refers to the process of condensing a given text, like an article, document, or web page, into a shorter version that maintains the essential information and main concepts. Text summarization techniques can be broadly categorized into two main approaches: extractive methods and abstractive methods. Extractive summarization extracts important information from the source text, while abstractive summarization generates new sentences that capture the essence of the text. Summaries can be classified into two types: indicative, which represents only the main idea, and informative, which provides concise information from the document. To achieve abstractive text summarization, this research work proposes the Neural Network based Abstractive Text Summarization (NN_ATS) algorithm, which is compared against commonly used techniques such as Decision Tree and Naïve Bayes algorithms. The system accepts inputs in the form of URLs, local file paths, or plain texts. Experimental results demonstrate that the proposed NN_ATS algorithm outperforms other techniques in summarizing both single documents and multiple documents.