An Efficient Subtopic Retrieval System using Hybrid Approach

摘要

The subtopic retrieval is ?nding documents that cover many different subtopics of a query topic. It means the utility of a document in a ranking is dependent on other documents in the ranking. Subtopic retrieval has challenges for improving performance, as well as for developing effective algorithms. Current Ranking systems having some inability to support subtopic retrieval system. Two main postprocessing techniques for search results are clustering and diversification. Clustering and diversification are two essential methods which have been getting used for the last couple of years in the searching methods at search engine optimization. In this work we proposed an efficient hybrid approach using both diversification & clustering technique where agglomerative clustering is used & for diversification max min diversification is used. This reduces the overburden of the processor in terms of searching optimization. In this we also compared our hybrid results with previous results in terms of precision & recall which proves that our new hybrid approach has better results.