Building a filtering test collection for TREC 2002

Abstract

Test collections for the filtering track in TREC have typically used either past sets of relevance judgments, or categorized collections such as Reuters Corpus Volume 1 or OHSUMED, because filtering systems need relevance judgments during the experiment for training and adaptation. For TREC 2002, we constructed an entirely new set of search topics for the Reuters Corpus for measuring filtering systems. Our method for building the topics involved multiple iterations of feedback from assessors, and fusion of results from multiple search systems using different search algorithms. We also developed a second set of "inexpensive" topics based on categories in the document collection. We found that the initial judgments made for the experiment were sufficient; subsequent pooled judging changed system rankings very little. We also found that systems performed very differently on the category topics than on the assessor-built topics.