Method for automated sentence planning in a task classification system

• US 7,574,362 B2
• Filed: 03/11/2002
• Issued: 08/11/2009
• 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 L
• Application Number:
  US10/258,849
• Publication Number:
  US 20040098245A1
• Time in Patent Office: 2,710 Days
• Field of Search: 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 for sentence planning in a task classification system that interacts with a user, comprising:

recognizing symbols in a user'"'"'s single input communication to a task classification system;

determining whether the user'"'"'s input communication can be understood, wherein if the user'"'"'s communication can be understood, understanding data is generated;

generating a plurality of communicative goals based on the recognized symbols and understanding data, the generated plurality of communicative goals being related to information needed to be obtained from the user;

in response to information from the user'"'"'s single input communication;

generating a plurality of sentence plans based on the plurality of generated communicative goals, 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 the 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;

independent of the user, ranking the plurality of generated sentence plans; and

outputting at least one of the ranked sentence plans to the user as a response to the user'"'"'s single input communication such that one dialog turn occurs starting with the user'"'"'s single input communication and ending with the outputted sentence plan.

2. The method of claim 1, wherein the automatically planning step further comprises:

selecting the highest ranked sentence plan.

3. 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.

4. The method of claim 1, 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.

5. 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 task classification system, wherein the generating a plurality of sentence plans step generates sentence plans using the interaction information.

6. The method of claim 1, wherein if the recognized symbols could not be understood, dialog is conducted with the user.

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

8. The method of claim 7, wherein the nonverbal communications include 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 communicative goals have been met; and

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

10. 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 system'"'"'s interactions with the user if the determining step determines that all of the communicative goals have been met.

11. The method of claim 1, wherein the generated communicative goals include confirming information previously obtained from the user.

12. The method of claim 1, further comprising:

converting at least one of the ranked sentence plans from text to speech.

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

14. A method for automatically planning a sentence in a task classification system, comprising:

recognizing symbols in a user'"'"'s single input communication;

determining whether the user'"'"'s input communication can be understood, wherein if the user'"'"'s communication can be understood, understanding data is generated;

generating a plurality of communicative goals based on the recognized symbols and understanding data, the generated plurality of communicative goals being related to information needed to be obtained from the user;

in response to information from the user'"'"'s single input communication;

generating a plurality of sentence plans based on the plurality of generated communicative goals, 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 the 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;

independent of the user, ranking the generated sentence plans;

selecting the highest ranked sentence plan;

realizing the selected sentence plan; and

outputting the realized sentence plan to the user as a response to the user'"'"'s single input communication such that a dialog turn occurs starting with the user'"'"'s single input communication and ending with the outputted sentence plan.

15. The method of claim 14, wherein the realizing step includes applying a set of linguistic rules to the selected sentence plan.

16. The method of claim 14, 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.

17. The method of claim 14, further comprising:

retrieving a discourse history database containing interaction information related to a set of interactions between the user and the automated dialog system, wherein the generating a plurality of sentence plans step generates sentence plans using the interaction information.

18. The method of claim 14, wherein if the symbols could not be understood, dialog is conducted with the user.

19. The method of claim 14, user'"'"'s input communication includes nonverbal communications.

20. The method of claim 19, wherein the nonverbal communications include 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.

21. The method of claim 14, further comprising:

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

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

22. The method of claim 14, further comprising:

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

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

23. The method of claim 14, wherein the communicative goals include confirming information previously obtained from the user.

24. The method of claim 14, further comprising:

converting the realized sentence plan from text to speech.

25. The method of claim 14, wherein the method 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. A method for automatically planning a sentence in a task classification system, comprising:

recognizing symbols in a user'"'"'s input communication;

determining whether the user'"'"'s single input communication can be understood, wherein if the user'"'"'s communication can be understood, understanding data is generated;

generating a plurality of communicative goals based on the recognized symbols and understanding data, the generated plurality of communicative goals being related to information needed to be obtained from the user;

in response to information from the user'"'"'s single input communication;

generating a plurality of sentence plans based on the communicative goals and information related to a set of interactions between the user and the automated dialog system, 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 the 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 generated sentence plans using a set of learned rules and independent of the user;

selecting the highest ranked sentence plan;

realizing the selected sentence plan by applying a set of linguistic rules;

converting the realized sentence plan from text to speech; and

outputting the converted sentence plan to the user as an immediate and single a response to the user'"'"'s single input communication such that a dialog turn occurs starting with the user'"'"'s single input communication and ending with the outputted sentence plan.

27. The method of claim 26, wherein if the symbols could not be understood, dialog is conducted with the user.

28. The method of claim 26, wherein user'"'"'s input communication includes nonverbal communications.

29. The method of claim 28, wherein the nonverbal communications include 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.

30. The method of claim 26, further comprising:

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

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

31. The method of claim 26, further comprising:

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

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

32. The method of claim 26, wherein the communicative goals include confirming information previously obtained from the user.

33. The method of claim 26, wherein the method is used in one of a customer care system, a reservation system, parts ordering system, navigation system, information gathering system, and information retrieval system.