Text summarization is a technique where the computer automatically creates an abstract
or summary of one or more texts. Initial interest towards automatic summarization
started in the 1960s in American research libraries (Luhn, 1958; and Edmundson, 1969).
As the amount of online information increases, more and more effort is dedicated to
create automatic summarization systems. Since the automatic text summarization is
largely a language-specific task, there has been a necessity to develop efficient
algorithms for it. A summary can be loosely defined as a text that is produced from one
or more texts that conveys important information in the original text and that is not
longer than half of the original text. In other words, the main goal of a summary is to
present the main ideas in a document in less space. Automatic text summarization is
a multifaceted endeavor that typically branches out in several dimensions (Sparck-
Jones, 1999).
Internet provides us with new perspectives, making the exchange of information not
only easier than ever but also virtually unrestricted. A person who wishes to know the
current happenings of an event via Internet surfs a number of news sites available. Mostly, he spends a lot of time reading different papers which have the same
information scattered in different ways. A researcher or academician tries to update his
knowledge by reading through the literature reviews published by different media.
However, it is not possible to read through the contents completely, as scientific papers
are updated day-to-day. There are millions of documents available on the web either in
new or repeated forms. It is very difficult for researchers to read the entire document
line by line to get the important points since it is time-consuming and difficult to
understand. The user has to spend a lot of time in reading, which may result in errors
like leaving the important points unread. There are chances that the user may leave the
entire document unread and may wish for a more simplified version. |
