Method for Automated Sentence Planning in a Task Classification System

• US 20110218807A1
• Filed: 05/18/2011
• Published: 09/08/2011
• Est. Priority Date: 03/14/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: RAMBOW, Owen Christopher, WALKER, Marilyn A., ROGATI, Monica
• Granted Patent: US 8,209,186 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• 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 method comprising:

receiving a single input communication from a user in a spoken dialog system;

generating, via a processor and in response to the single input communication, a plurality of communication goals, wherein the plurality of communication goals are ranked by a priority;

generating a plurality of sentence plans corresponding to the plurality of communication goals, wherein each sentence plan of the plurality of sentence plans comprises elementary speech acts and is a viable and potentially usable prompt in response to the single input communication; and

presenting to the user a selected sentence plan from the plurality of sentence plans as a response to the 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 single input communication from the user and ending with presentation of the selected sentence plan.

3. The method of claim 1, wherein the selected sentence plan corresponds to a selected communication goal, the selected communication goal ranking highest in the priority of the plurality of communication goals.

4. The method of claim 1, further comprising:

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

5. The method of claim 1, further comprising:

retrieving a training database that includes a set of learned rules, wherein ranking of the plurality of communication goals by priority is performed using the set of learned rules.

6. The method of claim 1, further comprising:

retrieving a discourse history 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.

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

8. The method of claim 7, 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.

9. The method of claim 1, further comprising:

determining whether all of the plurality of communication goals have been met; and

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

10. The method of claim 1, further comprising:

determining whether all of the plurality of communication goals have been met; and

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

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

a processor;

a first module configured to control the processor to receive a single input communication from a user in the spoken dialog system;

a second module configured to control the processor to generate, in response to the single input communication, a plurality of communication goals, wherein the plurality of communication goals are ranked by a priority;

a third module configured to control the processor to generate a plurality of sentence plans corresponding to the plurality of communication goals, wherein each sentence plan of the plurality of sentence plans comprises elementary speech acts and is a viable and potentially usable prompt in response to the single input communication; and

a fourth 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 single input communication.

12. The system of claim 11, wherein the fourth module is further configured to control the processor to present the selected sentence plan such that one dialog turn occurs starting with the single input communication from the user and ending with presentation of the selected sentence plan.

13. The system of claim 11, wherein the selected sentence plan corresponds to a selected communication goal, the selected communication goal ranking highest in the priority of the plurality of communication goals.

14. The system of claim 11, further comprising:

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

15. The system of claim 11, further comprising:

a fifth module configured to control the processor to retrieve a training database that includes a set of learned rules, wherein ranking of the plurality of communication goals by priority is performed using the set of learned rules.

16. The system of claim 11, further comprising:

a fifth 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.

17. The system of claim 11, wherein interactions between the user and the spoken language dialog system include a nonverbal communication.

18. A non-transitory computer-readable medium storing a computer program having instructions which when executed by a processor control the processor, the instructions comprising:

receiving a single input communication from a user in a spoken dialog system;

generating, via a processor and in response to the single input communication, a plurality of communication goals, wherein the plurality of communication goals are ranked by a priority;

generating a plurality of sentence plans corresponding to the plurality of communication goals, wherein each sentence plan of the plurality of sentence plans comprises elementary speech acts and is a viable and potentially usable prompt in response to the single input communication; and

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

19. The non-transitory computer-readable medium of claim 18, wherein presenting the selected sentence plan to the user such that one dialog turn occurs starting with the single input communication from the user and ending with presentation of the selected sentence plan.

20. The non-transitory computer-readable medium of claim 18, wherein the selected sentence plan corresponds to a selected communication goal, the selected communication goal ranking highest in the priority of the plurality of communication goals.