METHOD FOR AUTOMATED SENTENCE PLANNING IN A TASK CLASSIFICATION SYSTEM

• US 20090276225A1
• Filed: 07/10/2009
• Published: 11/05/2009
• Est. Priority Date: 03/14/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Walker, Marilyn A., Rambow, Owen Christopher, Rogati, Monica
• Granted Patent: US 7,949,537 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

The invention relates to a method for sentence planning (120) in a task classification system that interacts with a user. The method may include recognizing symbols in the user'"'"'s input communication and determining whether the user'"'"'s input communication can be understood. If the user'"'"'s communication can be understood, understanding data may be generated (220). The method may further include generating communicative goals (3010) based on the recognized symbols and understanding data. The generated communicative goals (3010) may be related to information needed to be obtained form the user. The method may also include automatically planning one or more sentences (3020) based on the generated communicative goals and outputting at least one of the sentence plans to the user (3080).

Claims

1. A computer-implemented method for interacting with a user in a spoken dialog system, the method comprising performing at least one of the following steps via a processor:

in response to information from a user'"'"'s single input communication in a spoken dialog system, generating a plurality of sentence plans each sentence plan in the plurality of sentence plans being a realization comprising elementary speech acts each corresponding to a respective communicative goal and combined into at least one complete sentence that accomplishes a plurality of communicative goals and wherein each sentence plan of the plurality of sentence plans is a viable and potentially usable prompt in response to the user'"'"'s single input communication;

ranking the plurality of generated sentence plans; and

presenting to the user a selected sentence plan from the plurality of sentence plans as a response to the user'"'"'s single input communication.

2. The method of claim 1, further comprising presenting the selected sentence plan such that one dialog turn occurs starting with the user'"'"'s single input communication and ending with the presented sentence plan.

3. The method of claim 1, further comprising ranking the plurality of sentence plans.

4. The method of claim 3, wherein the selected sentence plan is the highest ranked sentence plan of the plurality of the sentence plans.

5. The method of claim 1, further comprising:

realizing the selected sentence plan, wherein the realizing step includes applying a set of linguistic rules to the selected sentence plan.

6. The method of claim 3, further comprising:

retrieving a training database that includes a set of learned rules, wherein the ranking step is performed using the set of learned rules.

7. The method of claim 1, further comprising:

retrieving a discourse history database that includes interaction information related to a set of interactions between the user and the spoken dialog system, wherein the plurality of sentence plans are generated using the interaction information.

8. The method of claim 1, wherein interactions between the user and the spoken dialog system include a nonverbal communication.

9. The method of claim 8, wherein the nonverbal communication includes at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

10. The method of claim 1, further comprising:

determining whether all of the communicative goals have been met; and

routing information obtained from the system'"'"'s spoken dialog interactions with the user for task completion if the determining step determines that all of the communicative goals have been met.

11. The method of claim 1, further comprising:

determining whether all of the communicative goals have been met; and

processing any tasks associated with the information obtained from the spoken dialog system'"'"'s interactions with the user if the determining step determines that all of the communicative goals have been met.

12. A spoken dialog system, the spoken dialog system comprising:

a processor;

a module configured, in response to information from a user'"'"'s single input communication in a spoken dialog system, to control the processor to generate a plurality of sentence plans each sentence plan in the plurality of sentence plans being a realization comprising elementary speech acts each corresponding to a respective communicative goal and combined into at least one complete sentence that accomplishes a plurality of communicative goals and wherein each sentence plan of the plurality of sentence plans is a viable and potentially usable prompt in response to the user'"'"'s single input communication;

a module configured to control the processor to rank the plurality of generated sentence plans; and

a module configured to control the processor to present to the user a selected sentence plan from the plurality of sentence plans as a response to the user'"'"'s single input communication.

13. The system of claim 12, further comprising a module configured to control the processor to present the selected sentence plan such that one dialog turn occurs starting with the user'"'"'s single input communication and ending with the presented sentence plan.

14. The system of claim 12, further comprising a module configured to control the processor to rank the plurality of sentence plans.

15. The system of claim 14, wherein the selected sentence plan is the highest ranked sentence plan of the plurality of the sentence plans.

16. The system of claim 12, further comprising:

a module configured to control the processor to realize the selected sentence plan, wherein the realizing includes applying a set of linguistic rules to the selected sentence plan.

17. The system of claim 14, further comprising:

a module configured to control the processor to retrieve a training database that includes a set of learned rules, wherein the ranking is performed using the set of learned rules.

18. The system of claim 12, further comprising:

a module configured to control the processor to retrieve a discourse history database that includes interaction information related to a set of interactions between the user and the spoken dialog system, wherein the plurality of sentence plans are generated using the interaction information.

19. The system of claim 12, wherein interactions between the user and the spoken dialog system include a nonverbal communication.

20. A tangible computer-readable medium storing instructions for controlling a spoken dialog system, the instructions being carried out by a processor, the instructions comprising:

in response to information from a user'"'"'s single input communication in a spoken dialog system, generating a plurality of sentence plans each sentence plan in the plurality of sentence plans being a realization comprising elementary speech acts each corresponding to a respective communicative goal and combined into at least one complete sentence that accomplishes a plurality of communicative goals and wherein each sentence plan of the plurality of sentence plans is a viable and potentially usable prompt in response to the user'"'"'s single input communication;

ranking the plurality of generated sentence plans; and

presenting to the user a selected sentence plan from the plurality of sentence plans as a response to the user'"'"'s single input communication.