System and method for generating substitutable queries on the basis of one or more features

1. A method for generating one or more related queries with respect to a given query, the method comprising:

receiving a query comprising one or more terms;

segmenting the received query into one or more segments;

generating a corpus of candidate reformulations, wherein generating the corpus of candidate reformulations comprises generating a pair of successive queries or segments of one or more terms;

identifying one or more queries or terms from the corpus of candidate reformulations related to the received query;

generating one or more related queries on the basis of the identified one or more queries or terms from the corpus of candidate reformulations;

calculating probability scores for the one or more related queries indicating an extent to which the one or more related queries are related to the received query, the calculating the probability score for a related query including modifying the probability score associated with the related query based upon an analysis of one or more features associated with the received query and the related query; and

selecting one or more of the related queries with probability scores exceeding a given threshold;

wherein modifying the probability score associated with a given related query comprises:

performing an analysis of one or more query log features associated with the related query and the received query, including identifying a frequency with which a plurality of users rewrite the received query into the related query as indicated by a plurality of query logs from a plurality of users;

performing an analysis of one or more location features associated with the related query and the received query, including identifying a location specified by the received query; identifying a location specified by the related query; and identifying an extent to which the location specified by the received query is related to the location specified by the related query; and

modifying the probability score based upon the analysis.

2. The method of claim 1 wherein segmenting the received query comprises segmenting the received query into one or more terms or phrases.

3. The method of claim 1 wherein identifying comprises identifying one or more queries or terms from the corpus of the candidate reformulations related to the one or more segments of the received query.

4. The method of claim 1 wherein receiving a query comprises receiving from a user of a client device.

5. The method of claim 1 wherein generating a corpus of candidate reformulations comprises:

identifying one or more pairs of queries issued successively by one or more users of client devices; and

generating a corpus of candidate reformulations on the basis of the one or more identified pairs of queries.

6. The method of claim 1 wherein generating a corpus of candidate reformulations comprises:

segmenting one or more queries issued successively by one or more users of client devices;

identifying one or more differing segments between the successively issued queries; and

generating a corpus of candidate reformulations on the basis of the one or more segments.

7. The method of claim 1 wherein calculating a probability score for a given related query comprises:

calculating a substitution quality score for a related query; transforming the substitution quality score for the related query into a probability score.

8. The method of claim 1 , wherein modifying the probability score associated with a given related query comprises:

performing an analysis of one or more web features associated with the related query and the received query; and

modifying the probability score based upon the analysis.

9. The method of claim 8 wherein performing an analysis of a web feature comprises:

generating a result set comprising one or more content items responsive to the related query;

generating a result set comprising one or more content items responsive to the received query; and

identifying one or more content items common to the result set associated with the related query and the result set associated with the received query.

10. The method of claim 1 wherein modifying the probability score associated with a given related query comprises:

performing an analysis of one or more syntactic features associated with the related query and the received query; and

modifying the probability score based upon analysis.

11. The method of claim 1 wherein performing an analysis of a syntactic feature comprises identifying a number of tokens common to both the received query and the related query.

12. The method of claim 10 wherein performing an analysis of a syntactic feature comprises identifying a difference in a number of characters comprising the received query and the related query.

13. The method of claim 10 wherein performing an analysis of a syntactic feature comprises:

identifying a number of tokens common to both the received query and the related query;

calculating a quotient of the number of identified tokens and the number of tokens in the received query.

14. The method of claim 1 wherein modifying the probability score associated with a given related query comprises:

performing an analysis of one or more co-bid features associated with the related query and the received query; and

modifying the probability score based upon the analysis.

15. The method of claim 14 wherein an analysis of a co-bid feature comprises identifying a number of advertisers that provided bids for both the received query and the related query.

16. The method of claim 14 wherein an analysis of a co-bid feature comprises identifying a number of advertisements associated with the received query and the related query.

17. The method of claim 1 wherein an identifying an extent to which the location specified by the received query is related to the location specified by the related query comprises identifying a value indicating a distance between the location specified by the received query and the location specified by the related query.