Automatic Multiple Document Text Summarization using Wordnet and Agility Tool
The number of web pages on the World Wide Web is increasing very rapidly. Consequently, search engines like Google, AltaVista, Bing etc. provides a long list of URLs to the end user. So, it becomes very difficult to review and analyze each web page manually. That’s why automatic text sumarization is used to summarize the source text into its shorter version by preserving its information content and overall meaning. This paper proposes an automatic multiple documents text summarization technique called AMDTSWA, which allows the end user to select multiple URLs to generate their summarized results in parallel. AMDTSWA makes the use of concept based segmentation, HTML DOM tree and concept blocks formation. Similarities of contents are determined by calculating the sentence score and useful information is extracted for generating a comparative summary. The proposed approach is implemented by using ASP.Net and gives good results.
