Get only the essential information: Text summarizer based on implicit data

Abstract

The need for a tool that takes a text and shortens it into a brief and succinct summary has never been greater than nowadays. With the huge amount of information on the internet and the necessity to get the essential of this information in a short time, the need for summarizers becomes everyday pressing, especially, for people with special needs like blind or elderly people. For those people it is vital to go directly to the essential information rather than having to read through many passages. So far and trying to reach human capabilities, research in automatic summarization has been based on hypothesis that are both enabling and limiting. Thus, if we want machines to mimic human abilities, then they will need access to the same large variety of knowledge. The implicit is affecting the orientation and the argumentation of the text and consequently its summary. Most of Text Summarizers (TS) are processing as compressing the initial data and they necessarily suffer from information loss. TS are focusing on features of the text only, not on what the author intended or why the reader is reading the text. In this paper, we address this problem and we present a system focusing on acquiring knowledge that is implicit. Such system helps people with special needs to acquire the essential data. We principally spotlight the implicit information conveyed by the argumentative connectives such as: but, even, yet .... and their effect on the summary.