Information extraction in a natural language understanding system

• US 9,767,092 B2
• Filed: 08/15/2016
• Issued: 09/19/2017
• Est. Priority Date: 06/18/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Balchandran, Rajesh, Boyer, Linda M., Purdy, Gregory
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US15/236,793
• Publication Number:
  US 20160350281A1
• Time in Patent Office: 400 Days
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A method of extracting information from text within a natural language understanding system can include processing a text input through at least one statistical model for each of a plurality of features to be extracted from the text input. For each feature, at least one value can be determined, at least in part, using the statistical model associated with the feature. One value for each feature can be combined to create a complex information target. The complex information target can be output.

Claims

1. A method of extracting information from a text input received by a natural language understanding system, comprising:

parsing the text input to extract a plurality of features from the text input;

identifying a plurality of pre-existing statistical models;

processing, through the plurality of statistical models, each of the plurality of features to generate at least one value;

combining, via a processor, one value for each of the plurality of features to create a complex information target; and

outputting the complex information target, wherein

the complex information target indicates a meaning for the text input.

2. The method of claim 1, wherein

the plurality of statistical models output a plurality of candidate values for a particular feature,

a value having a highest confidence score is selected, for the particular feature, from the plurality of candidate values, and

the value having the highest confidence score is the one value, for the particular feature, used to create the complex information target.

3. The method of claim 1, further comprising:

searching the text input for at least one named entity; and

determining a value for a feature based upon the at least one named entity located within the text input.

4. The method of claim 1, further comprising:

determining a value for a first feature in the text input; and

selecting one of the plurality of statistical models based upon the value determined for the first feature.

5. The method of claim 4, wherein

the selected statistical model is built using a subset of the plurality of features that correspond to the determined value for the first feature.

6. The method of claim 1, further comprising:

comparing the complex information target with a plurality of allowable complex information targets; and

determining whether the complex information target is allowable based upon the comparison.

7. The method of claim 6, further comprising,

selecting an alternate value for at least one feature of the complex information target from a plurality of candidate values based upon a confidence score.

8. The method of claim 7, wherein

the alternate value conforms to an allowable complex information target.

9. A method of extracting information from a text input having a first feature and a second feature using a natural language understanding system, comprising:

determining a first value for the first feature using a selected text processing technique;

selecting a statistical model from a plurality of statistical models associated with a second feature based upon the first value;

determining a second value for the second feature using the selected statistical model;

forming, using a processor, a complex information target by combining the first and second values; and

outputting the complex information target.

10. The method of claim 9, wherein

the selected text processing technique is a statistical model associated with the first feature.

11. The method of claim 9, wherein

the selected text processing technique is a named entity feature extraction technique.

12. The method of claim 9, further comprising:

comparing the complex information target with a plurality of allowable complex information targets; and

determining whether the complex information target is valid based upon the comparison.

13. A computer program product, comprising:

a hardware storage device having stored therein computer usable program code for extracting information from a text input received by a natural language understanding system,

the computer usable program code, which when executed by a computer hardware system, causes the computer hardware system to perform;

parsing the text input to extract a plurality of features from the text input;

identifying a plurality of pre-existing statistical models;

processing, through the plurality of statistical models, each of the plurality of features to generate at least one value;

combining, via a processor, one value for each of the plurality of features to create a complex information target; and

outputting the complex information target, wherein

the complex information target indicates a meaning for the text input.

14. The computer program product claim 13, wherein

the plurality of statistical models output a plurality of candidate values for a particular feature,

a value having a highest confidence score is selected, for the particular feature, from the plurality of candidate values, and

the value having the highest confidence score is the one value, for the particular feature, used to create the complex information target.

15. The computer program product claim 13, wherein the computer usable program code further causes the computer hardware system to perform:

searching the text input for at least one named entity; and

determining a value for a feature based upon the at least one named entity located within the text input.

16. The computer program product claim 13, wherein the computer usable program code further causes the computer hardware system to perform:

determining a value for a first feature in the text input; and

selecting one of the plurality of statistical models based upon the value determined for the first feature.

17. The computer program product claim 13, wherein the computer usable program code further causes the computer hardware system to perform:

comparing the complex information target with a plurality of allowable complex information targets; and

determining whether the complex information target is allowable based upon the comparison.

18. The computer program product claim 13, wherein the computer usable program code further causes the computer hardware system to perform:

selecting an alternate value for at least one feature of the complex information target from a plurality of candidate values based upon a confidence score.

19. The computer program product claim 18, wherein

the alternate value conforms to an allowable complex information target.