Event-based summarization of news articles

Abstract

In recent years, with the increase of available digital information on the Web, the time needed to findrelevant information is also increased. Therefore, to reduce the time spent on searching, research on automatic textsummarization has gained importance. The proposed summarization process is based on event extraction methods andis called an event-based extractive single-document summarization. In this method, the important features of eventextraction and summarization methods are analyzed and combined together to extract the summaries from single-sourcenews documents. Among the tested features, six features are found to be the most effective in constructing goodsummaries. The constructed summaries are tested on benchmark Document Understanding Conferences 2001 and 2002datasets, and the results outperformed most of the other well-known summarization methods.