Conceptual Framework for Abstractive Text Summarization

Abstract

As the volume of information available on the Internet increases, there is a growing need for tools helping users to find, filter and manage these resources. While more and more textual information is available on- line, effective retrieval is difficult without proper indexing and summarization of the content. One of the possible solutions to this problem is abstractive text summarization. The idea is to propose a system that will accept single document as input in English and processes the input by building a rich semantic graph and then reducing this graph for generating the final summary. Text summarization is one of the most popular research areas today because of the problem of the information overloading available on the web, and has increased the necessity of the more strong and powerful text summarizers. The condensation of information from text is needed and this can be achieved by text summarization by reducing the length of the original text. Text summarization is commonly classified into two types extractive and abstractive. Extractive summarization means extracting few sentences from the original document based on some statistical factors and adding them into summary. Extractive summarization usually tends to sentence extraction rather than summarization. Whereas abstractive summarization are more powerful than extractive summarization because they generate the sentences based on their semantic meaning. Hence this leads to a meaningful summarization which is more accurate than extractive summaries. Summarization by extractive just extracts the sentences from the original document and adds them to summary. Extractive method is based on statistical features not on semantic relation with sentences (2) and are easier to implement. Therefore the summary generated by this method tends to be inconsistent. Summarization by abstraction needs understanding of the original text and then generating the summary which is semantically related. It is difficult to compute abstractive summary because it needs understanding of complex natural language processing tasks. There are few issues of extractive summarization. Extracted sentences usually tend to be longer than average. Due to this, parts of the segments that are not essential for summary also get included, consuming space. Important or relevant information is usually spread across sentences, and extractive summaries cannot capture this (unless the summary is long enough to hold all those sentences). Conflicting information may not be presented accurately. Pure extraction often leads to problems in overall coherence of the summary. These problems become more severe in the multi-document case, since extracts are drawn from different sources. Therefore abstractive