System and method for deriving natural language representation of formal belief structures

• US 20020173960A1
• Filed: 01/10/2002
• Published: 11/21/2002
• Est. Priority Date: 01/12/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Ross, Steven I., MacAllister, Jeffrey G., Alweis, Julie F.
• Granted Patent: US 6,950,793 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• 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 2015/228 of application context

Abstract

A conversation manager processes spoken utterances from a user of a computer, and develops responses to the spoken utterances. The conversation manager includes a reasoning facility and a language generation module. Each response has a domain model associated with it. The domain model includes an ontology (i.e., world view for the relevant domain of the spoken utterances and responses), lexicon, and syntax definitions. The language generation module receives a response in the form of a formal belief structure from other components of the conversation manager. The reasoning facility selects a syntax template to use in generating a response output from the formal belief structure. The language generation module produces the response output based on the formal structure, the selected syntax template, and the domain model.

Claims

1. A computer method for generating a response output to be provided to a user of a computer;

the method comprising the steps of;

receiving a response representation specifying a structured output for use as the basis for the response output to the user, the response representation associated with a domain model for a speech-enabled application;

selecting a syntax template based on a goal-directed rule invoked in response to the response representation; and

producing the response output based on the selected syntax template, the response representation, and the domain model.

2. The computer method of claim 1, wherein the response representation is received from a reasoning facility that generates the response representation based on the domain model, a goal-directed rules database, and a spoken utterance provided by the user.

3. The computer method of claim 2, wherein the response representation is a goal or proposition based on the spoken utterance.

4. The computer method of claim 3, wherein the proposition comprises an attribute, an object, and a value.

5. The computer method of claim 1, wherein the step of selecting one of the syntax templates comprises generating a goal based on the response representation and determining the selected syntax template based on the goal-directed rule selected from a goal-oriented rules database based on the goal, the goal-directed rule identifying the selected syntax template.

6. The computer method of claim 1, wherein the domain model comprises an ontological description of the domain model based on entities, classes, and attributes, and a lexicon providing synonyms and parts of speech information for elements of the ontological description.

7. The computer method of claim 1, wherein the response output is a text string capable of conversion to audio output.

8. A system for generating a response output to be provided to a user of a computer, the system comprising:

a language generator for receiving a response representation specifying a structured output for use as the basis for the response output to the user, the response representation associated with a domain model for a speech-enabled application; and

a reasoning facility coupled to the language generator, the reasoning facility for selecting a syntax template based on a goal-directed rule invoked in response to the response representation, the language generator producing the response output based on the selected syntax template, the response representation, and the domain model.

9. The system of claim 8, wherein the language generator receives the response representation from the reasoning facility that generates the response representation based on the domain model, a goal-directed rules database, and a spoken utterance provided by the user.

10. The system of claim 9, wherein the response representation is a goal or proposition based on the spoken utterance.

11. The system of claim 10, wherein the proposition comprises an attribute, an object, and a value.

12. The system of claim 8, wherein the language generator generates a goal based on the response representation and provides the goal to the reasoning facility, and the reasoning facility determines the selected syntax template based on the goal-directed rule selected from a goal-oriented rules database based on the goal, the goal-directed rule identifying the selected syntax template.

13. The system of claim 8, wherein the domain model comprises an ontological description of the domain model based on entities, classes, and attributes, and a lexicon providing synonyms and parts of speech information for elements of the ontological description.

14. The system of claim 8, wherein the response output is a text string capable of conversion to audio output.

16. The computer program product of claim 15, wherein the response representation is received from a reasoning facility that generates the response representation based on the domain model, a goal-directed rules database, and a spoken utterance provided by the user.

17. The computer program product of claim 16, wherein the response representation is a goal or proposition based on the spoken utterance.

18. The computer program product of claim 17, wherein the proposition comprises an attribute, an object, and a value.

19. The computer program product of claim 15, wherein the set of computer program instructions includes instructions to generate a goal based on the response representation and determine the selected syntax template based on the goal-directed rule selected from a goal-oriented rules database based on the goal, the goal-directed rule identifying the selected syntax template.

20. The computer program product of claim 15, wherein the domain model comprises an ontological description of the domain model based on entities, classes, and attributes, and a lexicon providing synonyms and parts of speech information for elements of the ontological description.

21. The computer program product of claim 15, wherein the response output is a text string capable of conversion to audio output.

15. A computer program product comprising:

a computer usable medium for generating a response output to be provided to a user of a computer;

a set of computer program instructions embodied on the computer usable medium, including instructions to;

receive a response representation specifying a structured output for use as the basis for the response output to the user, the response representation associated with a domain model for a speech-enabled application;

select a syntax template based on a goal-directed rule invoked in response to the response representation; and

produce the response output based on the selected syntax template, the response representation, and the domain model.

22. A system for generating a response output to be provided to a user of a computer;

the system comprising;

means for receiving a response representation specifying a structured output for use as the basis for the response output to the user, the response representation associated with a domain model for a speech-enabled application;

means for selecting a syntax template based on a goal-directed rule invoked in response to the response representation; and

means for producing the response output based on the selected syntax template, the response representation, and the domain model.

23. A computer program propagated signal product comprising:

a computer usable propagated medium for generating a response output to be provided to a user of a computer; and

a set of computer program instructions embodied on the computer usable propagated medium, including instructions to;

receive a response representation specifying a structured output for use as the basis for the response output to the user, the response representation associated with a domain model for a speech-enabled application;

select a syntax template based on a goal-directed rule invoked in response to the response representation; and

produce the response output based on the selected syntax template, the response representation, and the domain model.