The abstract is complex, but in case you want a read:
An information retrieval system includes a query revision architecture providing one or more query revisers, each of which implements a query revision strategy. A query rank reviser suggests known highly-ranked queries as revisions to a first query by initially assigning a rank to all queries, and identifying a set of known highly-ranked queries (KHRQ). Queries with a strong probability of being revised to a KHRQ are identified as nearby queries (NQ). Alternative queries that are KHRQs are provided as candidate revisions for a given query. For alternative queries that are NQs, the corresponding known highly-ranked queries are provided as candidate revisions.
After reading the application, Marcia notes that the search engine aims to suggest phrases under the top 10 results based on ambiguity, behavioral statistics, and user-generated query revisions.
Forum discussion continues at WebmasterWorld.