Juru at TREC 2005: Query Prediction in the Terabyte and the Robust Tracks

Our experiments focus this year on the ad-hock tasks of the Ter- abyte and the Robust tracks. In both tracks we experimented with the query prediction technology we developed recently. In the Ter- abyte track, we investigated how query prediction can be used to improve federation of search results extracted from several in- dices. We show that federated search based on query prediction can achieve comparable results to single-index search. In the Robust track we trained a predictor over one collection (TREC-8) for pre- dicting query diculty over another collection (AQUAINT). The experimental results show that dicult