On Correcting Misspelled Queries in Email Search

We consider the problem of providing spelling corrections for misspelled queries in Email Search using user’s own mail data. A popular strategy for general query spelling correction is to generate corrections from query logs. However, this strategy is not effective in Email Search for two reasons: 1) query log of any single user is typically not rich enough to provide potential corrections for a new query 2) corrections generated using query logs of other users are not particularly useful since the mail data as well as search intent are highly specific to the user. We address the challenge of designing an effective spelling correction algorithm for Email Search in the absence of query logs. We propose SpEQ, a Machine Learning based approach that generates corrections for misspelled queries directly from the user’s own mail data.