A multi-criteria method for automatic web page summarization

Abstract . In this paper we propose an original method to automatically summarize Web pages. This method is based on statistics rather than linguistics. It differs from most other methods by its ability to generate summaries with textual content as well as non textual content (images/graphics). Our method consists of a multi-criteria analysis to determine the salient content to be considered in the summary. The method has been implemented and integrated into a fully automated Web page summarization system. Keywords : Web pages, Automatic summarization, Multi-criteria analysis, Textual content, Non textual content, Selection criteria, Numerical approach.

• Type: Journal
• Year: 2015
• Where: NLDB
• Authors: Mehdi Belguith, Imen Touati, Mohamed Hédi Mâaloul, Iskandar Keskes
• Keywords: Natural Language Processing, NLDB 2015