Shadow Document Methods of Results Merging

摘要

In distributed information retrieval systems, document overlaps occur frequently across results from different databases. This is especially the case for meta-search engines which merge results from several general-purpose web search engines. This paper addresses the problem of merging results which contain overlaps in order to achieve better performance. Several algorithms for merging results are proposed, which take advantage of the use of duplicate documents in two ways: one correlates scores from different results; the other regards duplicates as increasing evidence of being relevant to the given query. A variety of experiments have demonstrated that these methods are effective.