ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Improving query focused summarization using look-ahead strategy

Badrinath, Rama and Venkatasubramaniyan, Suresh and Veni Madhavan, CE (2011) Improving query focused summarization using look-ahead strategy. In: ECIR 2011, 33rd European Conference on IR Research, April 18-21, 2011, Dublin, Ireland.

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1007/978-3-642-20161-5_64


Query focused summarization is the task of producing a compressed text of original set of documents based on a query. Documents can be viewed as graph with sentences as nodes and edges can be added based on sentence similarity. Graph based ranking algorithms which use 'Biased random surfer model' like topic-sensitive LexRank have been successfully applied to query focused summarization. In these algorithms, random walk will be biased towards the sentences which contain query relevant words. Specifically, it is assumed that random surfer knows the query relevance score of the sentence to where he jumps. However, neighbourhood information of the sentence to where he jumps is completely ignored. In this paper, we propose look-ahead version of topic-sensitive LexRank. We assume that random surfer not only knows the query relevance of the sentence to where he jumps but he can also look N-step ahead from that sentence to find query relevance scores of future set of sentences. Using this look ahead information, we figure out the sentences which are indirectly related to the query by looking at number of hops to reach a sentence which has query relevant words. Then we make the random walk biased towards even to the indirect query relevant sentences along with the sentences which have query relevant words. Experimental results show 20.2% increase in ROUGE-2 score compared to topic-sensitive LexRank on DUC 2007 data set. Further, our system outperforms best systems in DUC 2006 and results are comparable to state of the art systems.

Item Type: Conference Paper
Publisher: Springer-Verlag Berlin
Additional Information: Copyright of this article belongs to Springer-Verlag Berlin. GERMANY
Keywords: Topic Sensitive Lex Rank;Look-Ahead;Biased Random Walk
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Date Deposited: 19 Mar 2013 09:31
Last Modified: 19 Mar 2013 09:31
URI: http://eprints.iisc.ac.in/id/eprint/46040

Actions (login required)

View Item View Item