Method for automated sentence planning in a task classification system

• US 8,209,186 B2
• Filed: 05/18/2011
• Issued: 06/26/2012
• Est. Priority Date: 03/14/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Walker, Marilyn A., Rambow, Owen Christopher, Rogati, Monica
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US13/110,628
• Publication Number:
  US 20110218807A1
• Time in Patent Office: 405 Days
• Field of Search: 704/9, 704270-275
• 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 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 based on a dialog strategy;

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.

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 the plurality of sentence plans are ranked using the set of learned rules.

6. The method of claim 1, further comprising:

retrieving a discourse history comprising 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 comprises 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 system comprising:

a processor; and

a computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform a method comprising;

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

generating, in response to the single input communication, a plurality of communication goals, wherein the plurality of communication goals are based on a dialog strategy;

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.

12. The system of claim 11, the computer-readable storage medium storing further instructions which, when executed by the processor, cause the processor to perform a method 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.

13. The system of claim 11, wherein the selected sentence plan corresponds to a selected communication goal.

14. The system of claim 11, the computer-readable storage medium storing further instructions which, when executed by the processor, cause the processor to perform a method further comprising:

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

15. The system of claim 11, the computer-readable storage medium storing further instructions which, when executed by the processor, cause the processor to perform a method further comprising:

retrieving a training database that comprises a set of learned rules, wherein the plurality of sentence plans are ranked using the set of learned rules.

16. The system of claim 11, the computer-readable storage medium storing further instructions which, when executed by the processor, cause the processor to perform a method further comprising:

retrieving a discourse history database that comprises 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 having stored therein instructions which, when executed by a processor, cause the processor to perform a method comprising:

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

generating, in response to the single input communication, a plurality of communication goals, wherein the plurality of communication goals are based on a dialog strategy;

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, the instructions which, when executed by the processor, cause the processor to perform a method further comprising 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.