Distributed NLU/NLP

• US 20140136183A1
• Filed: 11/12/2012
• Published: 05/15/2014
• Est. Priority Date: 11/12/2012
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Hebert, Matthieu, Robichaud, Jean-Philippe, Parisien, Christopher M.
• Granted Patent: US 9,171,066 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/085 Methods for reducing search complexity, pruning
• CPC Class Codes: G10L 2015/228 of application context

Abstract

An arrangement and corresponding method are described for distributed natural language processing. A set of local data sources is stored on a mobile device. A local natural language understanding (NLU) match module on the mobile device performs natural language processing of a natural language input with respect to the local data sources to determine one or more local interpretation candidates. A local NLU ranking module on the mobile device processes the local interpretation candidates and one or more remote interpretation candidates from a remote NLU server to determine a final output interpretation corresponding to the natural language input.

Claims

1. An arrangement for distributed natural language processing comprising:

a set of local data sources stored on a mobile device;

a local natural language understanding (NLU) match module on the mobile device for natural language processing a natural language input with respect to the local data sources to determine one or more local interpretation candidates; and

a local NLU ranking module on the mobile device for processing the local interpretation candidates and one or more remote interpretation candidates from a remote NLU server to determine a final output interpretation corresponding to the natural language input.

2. An arrangement according to claim 1, wherein the NLU ranking module uses a fuzzy match algorithm to determine the final output interpretation.

3. An arrangement according to claim 1, wherein the NLU ranking module ranks the interpretation candidates in an N-Best list.

4. An arrangement according to claim 1, wherein the NLU ranking module further processes remote interpretation candidates identified as related to information represented in the local data sources before determining the final output interpretation.

5. An arrangement according to claim 4, wherein the local NLU ranking module further uses additional supplemental remote interpretation data from the remote NLU server together with data from the local data sources to determine the final output interpretation.

6. An arrangement according to claim 1, wherein the mobile device forwards natural language processing results of the NLU match module to the remote NLU server for developing the remote interpretation candidates.

7. An arrangement according to claim 1, wherein the local NLU ranking module further considers ranking data from the remote NLU server to determine the final output interpretation.

8. A method for distributed natural language processing comprising:

processing a natural language input on a mobile device with respect to local data sources stored on the mobile device to determine one or more local interpretation candidates; and

determining a final output interpretation corresponding to the natural language input by processing at the mobile device the local interpretation candidates and one or more remote interpretation candidates from a remote NLU server.

9. A method according to claim 8, wherein the final output interpretation is determined based on a fuzzy match algorithm.

10. A method according to claim 8, wherein processing the interpretation candidates includes ranking the interpretation candidates in an N-Best list.

11. A method according to claim 8, wherein before determining the final output interpretation, the mobile device further processes remote interpretation candidates identified as related to information represented in the local data sources.

12. A method according to claim 11, wherein the mobile device further uses additional supplemental remote interpretation data from the remote NLU server together with data from the local data sources to determine the final output interpretation.

13. A method according to claim 8, wherein processing the natural language input on the mobile device further includes forwarding natural language processing results to the remote NLU server for developing the remote interpretation candidates.

14. A method according to claim 8, wherein determining the final output interpretation further includes processing ranking data from the remote NLU server to determine the final output interpretation.