Generating query refinements from user preference data

摘要

Methods, systems, and apparatus, including computer program products, for generating query refinements from user preference data. A group of query pairs are obtained. Each query pair includes a first query and a second query. A quality score is determined for each query pair from user preference data for documents responsive to both the first and the second query. A diversity score is determined for each query pair having a quality score satisfying a quality threshold, the diversity score determined from user preference data for documents responsive to the second, but not the first, query. For each query pair having a quality score satisfying the quality threshold and a diversity score satisfying a diversity threshold, the second query of the query pair is associated with the first query of the query pair as a candidate refinement for the first query.

主权项

1. A computer-implemented method, comprising:
obtaining a group of query pairs, each query pair including a first query and a second query; determining, using one or more computers, a quality score for each query pair in the group of query pairs; determining a diversity score for each query pair in the group of query pairs having a quality score satisfying a quality threshold; and associating, for each query pair having a quality score satisfying the quality threshold and a diversity score satisfying a diversity threshold, the second query of the query pair with the first query of the query pair as a candidate refinement for the first query; selecting a group of candidate refinements associated with a candidate query, the group of candidate refinements ordered according to an order; processing one or more of the candidate refinements according to the order and determining, for at least one additional candidate refinement in the one or more processed candidate refinements, that the additional candidate refinement has an intra-suggestion diversity score satisfying an intra-suggestion diversity threshold, the intra-suggestion diversity score estimating diversity between a first group of top documents responsive to the additional candidate refinement and a group of seen documents; associating the additional candidate refinement with the candidate query as a confirmed refinement; and adding the first group of top documents to the group of seen documents.