|Searching Web Documents Using a Summarization Approach
|Year of Publication
|Qumsiyeh R, Ng Y-K D
|International Journal of Web Information Systems
Web search engines, such as Google, Bing, and Yahoo!, rank the set of documents S retrieved in response to a user query and represent each document D in S using a title and a snippet, which serves as an abstract of D. Snippets, however, are not as useful as they are designed for, i.e., assisting its users to quickly identify results of interest. These snippets are inadequate in providing distinct information and capture the main contents of the corresponding documents. Moreover, when the intended information need specified in a search query is ambiguous, it is very difficult, if not impossible, for a search engine to identify precisely the set of documents that satisfy the user’s intended request without requiring additional information. Furthermore, a document title is not always a good indicator of the content of the corresponding document either.
We propose to develop a query-based summarizer, called QSum in solving the existing problems of web search engines which use titles and abstracts in capturing the contents of retrieved documents. QSum generates a concise/comprehensive summary for each cluster of documents retrieved in response to a user query, which saves the user’s time and effort in searching for specific information of interest by skipping the step to browse through the retrieved documents one by one.
Experimental results show that QSum is effective and efficient in creating a high-quality summary for each cluster to enhance web search.
Our proposed query-based summarizer, QSum, is unique based on its searching approach. QSum is also a significant contribution to the web search community, since it handles the ambiguous problem of a search query by creating summaries in response to different interpretations of the search which offer a “road map” to assist users to quickly identify information of interest.