Adaptive task framework

• US 20070106495A1
• Filed: 11/09/2005
• Published: 05/10/2007
• Est. Priority Date: 11/09/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Katariya, Sanjeev, Ramsey, William, Barklund, Jonas
• Granted Patent: US 7,606,700 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

The subject disclosure pertains to systems and methods for performing natural language processing in which natural language input is mapped to a task. The system includes a task interface for defining a task, the associated data and the manner in which the task data is interpreted. Furthermore, the system provides a framework that manages the tasks to facilitate natural language processing. The task interface and framework can be used to provide natural language processing capabilities to third party applications. Additionally, the task framework can learn or be trained based upon feedback received from the third party applications.

Claims

1. A task defining method for natural language processing, comprising:

generating metadata related to a task;

defining one or more slots for the task; and

updating the task based upon user feedback.

2. The method of claim 1, further comprising:

generating at least one keyword related to the task function, the task is selected based at least in part upon the at least one keyword.

3. The method of claim 1, further comprising:

defining one or more entities;

defining one or more recognizers that are capable of identifying the one or more entities within the natural language input.

4. The method of claim 1, further comprising generating a description for the task.

5. The method of claim 1, updating the task includes updating the at least one keyword or modifying the one or more slots.

6. The method of claim 1, further comprising retrieving user feedback based in part on a query to task mapping.

7. The method of claim 6, further comprising retrieving the user feedback based in part on a query to slots mapping.

8. The system of claim 6, further comprising a component to update at least one ranking model based in part on user feedback.

9. The system of claim 7, the user feedback is employed to train at least one slot mapping component.

10. A natural language processing system, comprising:

a task component that employs metadata to describe at least one task;

a slot component that maps application data to the task; and

an interface component that links components of the task with at least one application.

11. The system of claim 10, the metadata includes an extensible field of at least one key and value pair.

12. The system of claim 10, further comprising a component to update the task based in part on user feedback.

13. The system of claim 10, the task component includes an entity component that includes at least one named entity, the named entity associated with at least one token that is assigned a specific meaning.

14. The system of claim 13, further comprising a recognizer component that includes one or more recognizers capable of matching tokens or portions of a natural language input to the at least one named entity.

15. The system of claim 10, the slot component is employed to define parameters for a respective task, the parameters including at least one of a slot name and a slot type.

16. The system of claim 15, the slot component is associated with one or more annotations.

17. The system of claim 10, the application executes a task directly using a semantic solution generated by a natural language processor.

18. The system of claim 10, the interface component includes at least one of a string component, a property component, a restatement component, and an execute component.

19. The system of claim 10, further comprising a computer readable medium having computer readable instructions stored thereon for executing the task component, the slot component, or the interface component.

20. A natural language processor, comprising:

means for defining at least one slot;

means for associating the slot with at least one keyword;

means for defining an entity for the slot; and

means for interfacing a task to the slot.