Frequently Asked Questions Web Pages Automatic Text Summarization

Yassien M. Shaalan and Ahmed Rafea

Keywords

Web Document Summarization, FAQ, Question Answering, Web Page Segmentation

Abstract

This research is directed towards automating frequently asked questions Web pages summarization, a task that captures the most salient pieces of information in answers of each question. To achieve this objective, an approach,which applies Web page segmentation to detect Q/A along with the use of some selective statistical sentence extraction features for summary generation, is proposed.The automatically generated summaries are compared to summaries generated by a widely used commercial tool named Copernic Summarizer2.1. The comparison isperformed via a formal evaluation process involving human evaluators. Statistical evaluation and analysis of the results demonstrate that our automatically generated summaries are significantly more informative than the commercial tool with approximately 19.5%.

Important Links:



Go Back