Generating query refinements from user preference data

A computer program product encoded on a computer storage medium, operable to cause data processing apparatus to perform operations comprising:

• obtaining a group of query pairs, each query pair including a first query and a second query;
• determining a quality score for each query pair in the group of query pairs from user preference data for documents responsive to both the first and the second query, wherein the user preference data for documents responsive to both the first and the second query is obtained from user preference data generated based on actions of a group of users, the actions including submitted queries and results responsive to the queries that are selected by respective users;
• determining a diversity score for each query pair in the group of query pairs 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;
• 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.

A system comprising one or more computers programmed to perform operations comprising:

• obtaining a group of query pairs, each query pair including a first query and a second query;
• determining a quality score for each query pair in the group of query pairs from user preference data for documents responsive to both the first and the second query, wherein the user preference data for documents responsive to both the first and the second query is obtained from user preference data generated based on actions of a group of users, the actions including submitted queries and results responsive to the queries that are selected by respective users;
• determining a diversity score for each query pair in the group of query pairs 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;
• 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.