Automated sentence planning in a task classification system

• US 7,516,076 B2
• Filed: 03/11/2002
• Issued: 04/07/2009
• Est. Priority Date: 03/14/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Walker, Marilyn A., Rogati, Monica, Rambow, Owen Christopher
• Primary Examiner(s): Edouard, Patrick N
• Assistant Examiner(s): Yen, Eric
• Application Number:
  US10/258,532
• Publication Number:
  US 20030110037A1
• Time in Patent Office: 2,584 Days
• Field of Search: 704270-275
• US Class Current: 704/275
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• 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: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

The invention relates to a task classification system (900) that interacts with a user. The task classification system (900) may include a recognizer (920) that may recognize symbols in the user'"'"'s input communication, and a natural language understanding unit (900) that may determine whether the user'"'"'s input communication can be understood. If the user'"'"'s input communication can be understood, the natural language understanding unit (930) may generate understanding data. The system may also include a communicative goal generator that may generate communicative goals based on the symbols recognized by the recognizer (920) and understanding data from the natural language understanding unit (930). The generated communicative goals may be related to information needed to be obtained from the user. The system may further include a sentence planning unit (120) that may automatically plan one or more sentences based on the communicative goals generated by the communicative goal generator with at least one of the sentences plans being output to the user.

Claims

1. A task classification system that interacts with a user, comprising:

a recognizer that recognizes symbols in the user'"'"'s input communication;

a natural language understanding unit that determines whether the user'"'"'s input communication can be understood, wherein if the user'"'"'s communication can be understood, the natural language understanding unit generates understanding data;

a communicative goal generator that generates a plurality of communicative goals based on the symbols recognized by the recognizer and understanding data from the natural language understanding unit, the generated plurality of communicative goals being related to information needed to be obtained from the user and based on the user'"'"'s input communication which is a communication which immediately precedes the generation of the plurality of communicative goals;

a sentence plan generator that generates a plurality of sentence plans based on the plurality of communicative goals generated by the communicative goal generator, each sentence plan of the plurality of sentence plans being a viable and potentially usable prompt in response to the user'"'"'s input; and

a sentence plan ranker that, independent of the user, ranks the plurality of sentence plans generated by the sentence plan generator, wherein at least one of the ranked sentence plans is output to the user, and wherein the user'"'"'s input communication and the output at least one ranked sentence plan comprise a single dialog turn in a spoken dialog including the user'"'"'s input communication and the output at least one ranked sentence plan.

2. The system of claim 1, wherein the sentence plan ranker selects the highest ranked sentence plan.

3. The system of claim 1, further comprising:

a realization unit that realizes the sentence plan selected by the sentence plan ranker unit by applying a set of linguistic rules.

4. The system of claim 1, further comprising:

a training database that includes a set of learned rules, wherein the sentence plan ranker ranks the plurality of sentence plans generated by the sentence plan generator using the set of learned rules.

5. The system of claim 1, further comprising:

a discourse history database that includes interaction information related to a set of interactions between the user and the task classification system, wherein the sentence plan generator generates the plurality of sentence plans using the interaction information.

6. The system of claim 1, further comprising:

a dialog manager that conducts dialog with the user if the natural language understanding unit does not understand the recognized symbols.

7. The system of claim 6, wherein the dialog manager determines whether all of the communicative goals have been met.

8. The system of claim 7, further comprising:

a task classification processor that routes information obtained from the system'"'"'s interactions with the user for task completion if the dialog manager determines that all of the communicative goals have been met.

9. The system of claim 7, further comprising:

a task classification processor that processes any tasks associated with the information obtained from the system'"'"'s interactions with the user if the dialog manager determines that all of the communicative goals have been met.

10. The system of claim 1, wherein the communicative goal generator generates communicative goals that include confirming information previously obtained from the user.

11. The system of claim 1, further comprising:

a text-to-speech converter that converts at least one of the ranked sentence plans from text to speech.

12. The system of claim 1, wherein the task classification system is used in one of a customer care system, a reservation system, parts ordering system, navigation system, information gathering system, and information retrieval system.

13. The system of claim 1, wherein interactions between the user and the task classification system include nonverbal communications.

14. The system of claim 13, wherein the nonverbal communications include at least one of gestures, body movements, head movements, nonresponses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

15. A task classification system, comprising:

a recognizer that recognizes symbols in a user'"'"'s input communication;

a natural language understanding unit that determine whether the user'"'"'s input communication can be understood, wherein if the user'"'"'s communication can be understood, the natural language understanding unit generates understanding data;

a communicative goal generator that generates a plurality of communicative goals based on the symbols recognized by the recognizer and understanding data from the natural language understanding unit, the generated plurality of communicative goals being related to information needed to be obtained from the user and based on the user'"'"'s input communication which is a communication which immediately precedes the generation of the plurality of communicative goals;

a sentence plan generator that generates a plurality of sentence plans based on the plurality of communicative goals generated by the communicative goal generator, each sentence plan of the plurality of sentence plans being a viable and potentially usable prompt in response to the user'"'"'s input;

a sentence plan ranker that, independent of the user, ranks the generated sentence plans and selects the highest ranked sentence plan; and

a realization unit that realizes the selected sentence plan, wherein the realized sentence plan is output to the user, and wherein the user'"'"'s input communication and the output at least one ranked sentence plan comprise a single dialog turn in a spoken dialog including the user'"'"'s input communication and the output at least one ranked sentence plan.

16. The system of claim 15, wherein the realization unit realizes the selected sentence by applying a set of linguistic rules.

17. The system of claim 15, further comprising:

a training database that includes a set of learned rules, wherein the sentence plan ranker ranks the plurality of sentence plans generated by the sentence plan generator using the set of learned rules.

18. The system of claim 15, further comprising:

a discourse history database that includes interaction information related to a set of interactions between the user and the task classification system, wherein the sentence plan generator generates the plurality of sentence plans using the interaction information.

19. The system of claim 15, further comprising:

a dialog manager that conducts dialog with the user if the natural language understanding unit does not understand the recognized symbols.

20. The system of claim 19, wherein the dialog manager determines whether all of the communicative goals have been met.

21. The system of claim 20, further comprising:

a task classification processor that routes information obtained from the system'"'"'s interactions with the user for task completion if the dialog manager determines that all of the communicative goals have been met.

22. The system of claim 20, further comprising:

a task classification processor that processes any tasks associated with the information obtained from the system'"'"'s interactions with the user if the dialog manager determines that all of the communicative goals have been met.

23. The system of claim 15, wherein the communicative goal generator generates communicative goals that include confirming information previously obtained from the user.

24. The system of claim 15, further comprising:

a text-to-speech converter that converts at least one of the one or more sentence plans from text to speech.

25. The system of claim 15, wherein the system is used in one of a customer care system, a reservation system, parts ordering system, navigation system, information gathering system, and-information retrieval system.

26. The system of claim 15, user'"'"'s input communication includes nonverbal communications.

27. The system of claim 26, wherein the nonverbal communications include at least one of gestures, body movements, head movements, nonresponses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

28. A task classification system, comprising:

a recognizer that recognizes symbols in a user'"'"'s input communication;

a natural language understanding unit that determines whether the user'"'"'s input communication can be understood, wherein if the user'"'"'s input communication can be understood, the natural language understanding unit generates understanding data;

a communicative goal generator that generates a plurality of communicative goals based on the symbols recognized by the recognizer and understanding data from the natural language understanding unit, the generated plurality of communicative goals being related to information needed to be obtained from the user and based on the user'"'"'s input communication which is a communication which immediately precedes the generation of the plurality of communicative goals;

a sentence plan generator that generates a plurality of sentence plans based on the plurality of communicative goals generated by the communicative goal generator and information related to a set of interactions between the user and the task classification system, each sentence plan of the plurality of sentence plans being a viable and potentially usable prompt in response to the user'"'"'s input;

a sentence plan ranker that, independent of the user, ranks the generated sentence plans using a set of learned rules and selects the highest ranked sentence plan;

a realization unit that realizes the selected sentence plan by applying a set of linguistic rules; and

a text-to-speech converter that converts the realized sentence plan from text to speech, wherein the converted sentence plan is output to the user, and wherein the user'"'"'s input communication and the output at least one ranked sentence plan comprise a single dialog turn in a spoken dialog including the user'"'"'s input communication and the output at least one ranked sentence plan.

29. The system of claim 28, further comprising:

a dialog manager that conducts dialog with the user if the natural language understanding unit does not understand the recognized symbols.

30. The system of claim 29, wherein the dialog manager determines whether all of the communicative goals have been met.

31. The system of claim 30, further comprising:

a task classification processor that routes information obtained from the system'"'"'s interactions with the user for task completion if the dialog manager determines that all of the communicative goals have been met.

32. The system of claim 30, further comprising:

a task classification processor that processes any tasks associated with the information obtained from the system'"'"'s interactions with the user if the dialog manager determines that all of the communicative goals have been met.

33. The system of claim 28, wherein user'"'"'s input communication includes nonverbal communications.

34. The system of claim 33, wherein the nonverbal communications include at least one of gestures, body movements, head movements, nonresponses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.

35. The system of claim 28, wherein the communicative goal generator generates communicative goals that include confirming information previously obtained from the user.

36. The system of claim 28, wherein the system is used in one of a customer care system, a reservation system, parts ordering system, navigation system, information gathering system, and information retrieval system.