USER QUERY HISTORY EXPANSION FOR IMPROVING LANGUAGE MODEL ADAPTATION

• US 20150325237A1
• Filed: 07/23/2015
• Published: 11/12/2015
• Est. Priority Date: 09/23/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Chang, Shuangyu, Levit, Michael, Buntschuh, Bruce Melvin
• Granted Patent: US 9,299,342 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/34 Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing

Abstract

Query history expansion may be provided. Upon receiving a spoken query from a user, an adapted language model may be applied to convert the spoken query to text. The adapted language model may comprise a plurality of queries interpolated from the user'"'"'s previous queries and queries associated with other users. The spoken query may be executed and the results of the spoken query may be provided to the user.

Claims

1. A computer-implemented method comprising:

receiving a spoken query from a user;

applying an adapted language model to process the spoken query, wherein the adapted language model processes data associated with the spoken query using a set of previous queries of the and previous query data of a plurality of other users that share at least one common characteristic with the set of previous queries of the user, wherein the common characteristic is selected uniform resource locator data included in the set of previous queries of the user and included in the previous query data of the plurality of other users; and

modifying the data associated with the spoken query based on the applying of the adapted language model.

2. The computer-implemented method of claim 1, wherein the receiving of the spoken query further comprises converting the spoken query to text, and wherein the modifying of the data associated with the spoken query further comprises modifying the converted text.

3. The computer-implemented method of claim 1, wherein the modifying of the data associated with the spoken query further comprises converting the spoken query to text for subsequent processing.

4. The computer-implemented method of claim 1, further comprising generating a personalized language model for the user based on the adapted language model, and applying the personalized language model to a subsequent query of the user.

5. The computer-implemented method of claim 1, wherein the applying of the adapted language model further comprises analyzing a click-query graph to identify the common characteristic between at least one previous query of the user and at least a previous query of another user, and using result data from the analyzing of the click-query graph to evaluate the spoken query.

6. The computer-implemented method of claim 5, wherein the query-click graph is a bipartite graph providing the previous query data in association with content of the selected uniform resource locator data.

7. The computer-implemented method of claim 1, wherein the applying of the adapted language model further comprises identifying a cluster of users that are associated with the previous query data, and using additional query data of the cluster of users to expand the adapted language model in the converting of the spoken query.

8. The computer-implemented method of claim 1, wherein the applying identifies, from the previous query data, queries that include the selected uniform resource locator that corresponds with content having a lexical similarity to the set of previous queries of the user, and the generating of the result data utilizes the identified queries to process the spoken query, and wherein the lexical similarity is at least one selected from a group consisting of:

a lexical match between the set of previous queries and the previous query data, a word class match between the set of previous queries and the previous query data, a phrase class match between the set of previous queries and the previous query data, a match in latent attributes between the set of previous queries and the previous query data, and a match in a query topic between the set of previous queries and the previous query data.

9. A system comprising:

at least one processor; and

a memory operatively connected with the processor storing instructions, that when executed on the processor causing the processor to execute operations that comprise;

creating an adapted language model to process queries received from a user, wherein the adapted language model expands a set of previous queries of the user by interpolating previous query data of a plurality of other users that share at least one common characteristic with the user, wherein the common characteristic is selected uniform resource locator data included in the set of previous queries of the user and included in the previous query data of the plurality of other users, and

processing data associated with the spoken query by applying the created adapted language model to the data associated with the spoken query.

10. The system of claim 9, wherein the processing of the data associated with the spoken query further comprises converting the spoken query to text for subsequent processing.

11. The system of claim 9, wherein the operations further comprising generating a personalized language model for the user based on the adapted language model, and applying the personalized language model to a subsequent query of the user.

12. The system of claim 9, wherein the processing comprises analyzing a click-query graph to identify the common characteristic between at least one previous query of the user and at least a previous query of another user, and using result data from the analyzing of the click-query graph to convert the spoken query.

13. The system of claim 12, wherein the query-click graph is a bipartite graph providing the previous query data in association with the content of the selected uniform resource locator data.

14. The system of claim 9, wherein the applying of the adapted language model further comprises identifying a cluster of users that are associated with the previous query data, and using additional query data of the cluster of users to expand the adapted language model in processing the data of the spoken query.

15. The system of claim 9, wherein the applying identifies, from the previous query data, a subset of queries that include selected uniform resource locator data that corresponds with the content having a lexical similarity to the set of previous queries of the user, and the generating of the result data utilizes the identified subset of queries to generate the result data, and wherein the lexical similarity is at least one selected from a group consisting of:

a lexical match between the set of previous queries and the previous query data, a word class match between the set of previous queries and the previous query data, a phrase class match between the set of previous queries and the previous query data, a match in latent attributes between the set of previous queries and the previous query data, and a match in a query topic between the set of previous queries and the previous query data.

16. A computer-readable storage medium which stores a set of instructions which when executed on at least one processor, the processor performs a method comprising:

receiving a spoken query from a user; and

applying an adapted language model to convert the spoken query to text,

wherein the adapted language model expands a set of previous queries of the user to be applied to covert the spoken query by incorporating previous query data of a plurality of other users that share at least one common characteristic with the set of previous queries of the user, wherein the common characteristic is selected uniform resource locator data included in the set of previous queries of the user and included in the previous query data of the plurality of other users.

17. The computer-readable storage medium of claim 16, wherein the method executed by the processor further comprises analyzing a click-query graph to identify the common characteristic between at least one previous query of the user and at least a previous query of another user, and converting the spoken query using result data from the analyzing of the click-query graph.

18. The computer-readable storage medium of claim 17, wherein the query-click graph is a bipartite graph providing the previous query data in association with content of the clicked uniform resource locator.

19. The computer-readable storage medium of claim 16, wherein the method executed by the processor further comprises generating a personalized language model for the user based on the adapted language model, and applying the personalized language model to a subsequent query of the user.

20. The computer-readable storage medium of claim 16, wherein the applying of the adapted language model further comprises identifying a cluster of users that are associated with the previous query data, and using additional query data of the cluster of users to convert the spoken query.