Accepted Papers

  • An Intelligent Web Search Using Multi-Document Summarization
    Sheetal A. Takale1 & Prakash J. Kulkarni2, 1Vidya Pratishthan's College of Engineering, India and 2Walchand College of Engineering, India
    Information available on the internet is huge, diverse and dynamic. Current Search Engine is doing the task of intelligent help to the users of the internet. For a given user query, it provides a listing of best-matching or relevant web pages. However, information for the query is often spread across multiple pages which are returned by the search engine. This degrades the quality of search results. So, the search engines are drowning in information, but starving for knowledge. In this paper we present a query focused extractive summarization of search engine results. For a given query it generates a summarized solution from all the search results returned by the search engine. The task of search result summarization is achieved as follows: Search Results returned by the search engine are ranked according to their semantic similarity with the user query. Semantic similarity is based on semantic roles. It is computed using NEC SENNA and WordNet. Top ranking search results are then clustered. For clustering, documents are represented as a term × document matrix. Clustering of documents is based on MDL principle. Further, these sentences are clustered using sentence × sentence similarity matrix and symmetric non-negative matrix factorization. From each cluster the top ranking sentences are selected based on their semantic score. Semantic score of each sentence is based on its importance within the cluster and with respect to user request. For performance analysis the system is tested using user survey. Experiments conducted demonstrate the effectiveness of system in semantic text understanding, document clustering and summarization. The better performance of system benefits from the sentence level semantic analysis, clustering using the MDL principle and SNMF.


Organized by