Marcin Kaszkiel and J. Zobel,
Ranking based on passages addresses some of the shortcomings of whole-document ranking. It provides convenient units of text to return to the user, avoids the difficulties of comparing documents of different length, and enables identification of short blocks of relevant material amongst otherwise irrelevant text. In this paper we consider a new approach to passage retrieval, based on an experimental exploration of the ability of passages to identify relevant documents. We compare our general scheme of passage retrieval to other document retrieval and passage retrieval methods, and use the results to propose a new method for simple, robust, and effective ranking based on fixed-length passages. Our experiments show that, compared to whole-document ranking, ranking via passages significantly improves retrieval effectiveness, by 8% for TREC disks 2 and 4 and by 18%-37% for the Federal Register collection.