We propose the use of learning to rank techniques to shorten query sessions by maximizing the probability that the query we predict is the "final" query of the current search session. We present a preliminary evaluation showing that this approach is a promising research direction.
Paper
Full text
Learning to shorten query sessions
Semantic Scholar · Computer Science · 2013
Abstract
We propose the use of learning to rank techniques to shorten query sessions by maximizing the probability that the query we predict is the "final" query of the current search session. We present a preliminary evaluation showing that this approach is a promising research direction.