Method and apparatus for dynamic modification of command weights in a natural language understanding system

• US 7,533,025 B2
• Filed: 06/11/2007
• Issued: 05/12/2009
• Est. Priority Date: 09/03/2003
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Coffman, Daniel Mark, Ramaswamy, Ganesh N., Kleindienst, Jan
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Sked; Matthew J
• Application Number:
  US11/761,079
• Publication Number:
  US 20070225969A1
• Time in Patent Office: 701 Days
• Field of Search: 704/257
• US Class Current: 704/275
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method and system for dynamically assigning weights to the subset of commands in a natural language dialog system based on prior context of the user'"'"'s interaction with the system. The search space of the translation process may be reduced when some context information is available. A user presents input to the natural language understanding system. The system translates the user input into a formal command and calculates a weight value for a next set of formal commands based on the formal command. The command weights may then be dynamically boosted for the next set of formal commands before executing the formal command. The exemplary aspects of the present invention reduce the time needed to complete a task since the search space of the translation process may be reduced if context information is available and improve the accuracy of the process by using knowledge that users regularly use repeating patterns for repeating tasks.

Claims

1. A method for context-based dynamic assignment of weights for formal commands in a natural language understanding system, comprising:

receiving a user input;

determining whether the user input is text-based;

responsive to determining that the user input is text-based, converting the user input into a text form to form a text input;

translating the text input into a formal command;

calculating a weight value for the formal command;

selecting a next set of formal commands;

determining weight values for the next set of formal commands based on the formal command before executing the formal command, wherein determining weight values for the next set of formal commands comprises computing weight values for the next set of formal commands based on a given command history, access method information, and application context, and wherein determining weight values for the next set of formal commands further comprises dynamically boosting command weights for a subset of formal commands of the next set of formal commands, wherein the subset of formal commands comprises a subset of formal commands that are considered more likely for translation of the user input than other formal commands of the set of formal commands and are given higher command weights than the other formal commands; and

executing the formal command.

2. The method of claim 1, further comprising:

receiving a second user input; and

translating the second user input into a formal command based on the boosted command weights.

3. The method of claim 1, further comprising:

resetting the boosted command weights to a default value.

4. The method of claim 3, wherein the step of resetting the boosted command weights includes automatically resetting the boosted command weights to the default value after the next set of formal commands are executed.

5. The method of claim 3, wherein the step of resetting the boosted command weights includes issuing a reset command by a dialog manager.

6. A data processing system for context-based dynamic assignment of weights for formal commands in a natural language understanding system, comprising:

a processor, the processor comprising;

means for receiving a user input;

means for determining whether the user input is text-based;

means responsive to determining that the user input is text-based, for converting the user input into a text form to form a text input;

means for translating the text input into a formal command;

means for selecting a next set of formal commands;

means for determining weight values for the next set of formal commands based on the formal command before executing the formal command, wherein determining weight values for the next set of formal commands comprises computing weight values for the next set of formal commands based on a given command history, access method information, and application context, and wherein the means for determining weight values for the next set of formal commands further comprises means for dynamically boosting command weights for a subset of formal commands of the next set of formal commands, wherein the subset of formal commands comprises a subset of formal commands that are considered more likely for translation of the user input than other formal commands of the set of formal commands and are given higher command weights than the other formal commands; and

means for executing the formal command.

7. The data processing system of claim 6, further comprising:

means for receiving a second user input; and

means for translating the second user input into a formal command based on the boosted command weights.

8. The data processing system of claim 6, further comprising:

means for resetting the boosted command weights to a default value.

9. The data processing system of claim 8, wherein the means for resetting the boosted command weights includes means for automatically resetting the boosted command weights to the default value after the next set of formal commands are executed.

10. The data processing system of claim 8, wherein the means for resetting the boosted command weights includes means for issuing a reset command by a dialog manager.

11. A computer program product comprising:

a computer readable recordable-type storage medium storing computer usable program code for context-based dynamic assignment of weights for formal commands in a natural language understanding system, the computer program product comprising;

computer usable program code for receiving a user input;

computer usable program code for determining whether the user input is text-based;

responsive to determining that the user input is text-based, computer usable program code for converting the user input into a text form to form a text input;

computer usable program code for translating the text input into a formal command;

computer usable program code for selecting a next set of formal commands;

computer usable program code for determining weight values for the next set of formal commands based on the formal command before executing the formal command, wherein the computer usable program code for determining weight values for the next set of formal commands comprises computer usable program code for computing weight values for the next set of formal commands based on a given command history, access method information, and application context, and wherein the computer usable program code for determining weight values for the next set of formal commands further comprises computer usable program code for dynamically boosting command weights for a subset of formal commands of the next set of formal commands, wherein the subset of formal commands comprises a subset of formal commands that are considered more likely for translation of the user input than other formal commands of the set of formal commands and are given higher command weights than the other formal commands; and

computer usable program code for executing the formal command.

12. The computer program product of claim 11, further comprising:

instructions for receiving a second user input; and

instructions for translating the second user input into a formal command based on the boosted command weights.

13. The computer program product of claim 11, further comprising:

instructions for resetting the boosted command weights to a default value.

14. The computer program product of claim 13, wherein the instructions for resetting the boosted command weights includes instructions for automatically resetting the boosted command weights to the default value after the next set of formal commands are executed.

15. The computer program product of claim 13, wherein the instructions for resetting the boosted command weights includes instructions for issuing a reset command by a dialog manager.