Learning from interactions for a spoken dialog system

• US 10,217,457 B2
• Filed: 04/10/2017
• Issued: 02/26/2019
• Est. Priority Date: 06/27/2006
• Status: Active Grant

• Current Assignee: AT&T Corporation (AT&T, Inc.), Rutgers University
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.), Rutgers University
• Inventors: Gilbert, Mazin, Levin, Esther, Littman, Michael Lederman, Schapire, Robert E.
• Primary Examiner(s): Ortiz-Sanchez, Michael
• Application Number:
  US15/483,213
• Publication Number:
  US 20170213546A1
• Time in Patent Office: 687 Days
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

In one embodiment, a semantic classifier input and a corresponding label attributed to the semantic classifier input may be obtained. A determination may be made whether the corresponding label is correct based on logged interaction data. An entry of an adaptation corpus may be generated based on a result of the determination. Operation of the semantic classifier may be adapted based on the adaptation corpus.

Claims

1. A method comprising:

obtaining a semantic classifier input for a semantic classifier and a corresponding label attributed to the semantic classifier input;

determining, via a processor, whether the corresponding label is correct based on logged interaction data, to yield a correctness result, wherein the logged interaction data comprises an input/output pair having an input and an output, the input comprising a speech recognition result in a lattice form and the output comprising one of an outcome of a call, a confirmation by a user, and a call hang-up; and

adapting operation of a spoken dialog system utilizing the semantic classifier based on the correctness result.

2. The method of claim 1, wherein the output as a result of the input.

3. The method of claim 1, wherein the logged interaction data further comprises:

data describing user speech; and

a non-speech user action indicating one of a negative training example and a positive training example.

4. The method of claim 1, further comprising:

generating an entry for an adaptation corpus based on the correctness result.

5. The method of claim 4, wherein adapting operation of the semantic classifier based on the correctness result further comprises adapting operation of the semantic classifier based on the adaptation corpus.

6. The method of claim 1, wherein determining whether the corresponding label is correct indicates whether the corresponding label attributed by the semantic classifier is one of a correct label and an incorrect label.

7. The method of claim 1, wherein determining whether the corresponding label is correct further comprises:

calculating a confidence level indicative of an estimated probability that the corresponding label attributed by the semantic classifier is correct to yield a calculated confidence level; and

determining that the corresponding label attributed by the semantic classifier is correct when the calculated confidence level is greater than a predetermined threshold.

8. A system comprising:

a processor; and

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

obtaining a semantic classifier input for a semantic classifier and a corresponding label attributed to the semantic classifier input;

determining whether the corresponding label is correct based on logged interaction data, to yield a correctness result, wherein the logged interaction data comprises an input/output pair having an input and an output, the input comprising a speech recognition result in a lattice form and the output comprising one of an outcome of a call, a confirmation by a user, and a call hang-up; and

adapting operation of a spoken dialog system utilizing the semantic classifier based on the correctness result.

9. The system of claim 8, wherein the output as a result of the input.

10. The system of claim 8, wherein the logged interaction data further comprises:

data describing user speech; and

a non-speech user action indicating one of a negative training example and a positive training example.

11. The system of claim 8, wherein the computer-readable storage medium stores additional instructions stored which, when executed by the processor, cause the processor to perform operations further comprising:

generating an entry for an adaptation corpus based on the correctness result.

12. The system of claim 11, wherein adapting operation of the semantic classifier based on the correctness result further comprises adapting operation of the semantic classifier based on the adaptation corpus.

13. The system of claim 8, wherein determining whether the corresponding label is correct indicates whether the corresponding label attributed by the semantic classifier is one of a correct label and an incorrect label.

14. The system of claim 8, wherein determining whether the corresponding label is correct further comprises:

calculating a confidence level indicative of an estimated probability that the corresponding label attributed by the semantic classifier is correct to yield a calculated confidence level; and

determining that the corresponding label attributed by the semantic classifier is correct when the calculated confidence level is greater than a predetermined threshold.

15. A computer-readable storage device having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:

obtaining a semantic classifier input for a semantic classifier and a corresponding label attributed to the semantic classifier input;

determining whether the corresponding label is correct based on logged interaction data, to yield a correctness result, wherein the logged interaction data comprises an input/output pair having an input and an output, the input comprising a speech recognition result in a lattice form and the output comprising one of an outcome of a call, a confirmation by a user, and a call hang-up; and

adapting operation of a spoken dialog system utilizing the semantic classifier based on the correctness result.

16. The computer-readable storage device of claim 15, wherein the output as a result of the input.

17. The computer-readable storage device of claim 15, wherein the logged interaction data further comprises:

data describing user speech; and

a non-speech user action indicating one of a negative training example and a positive training example.

18. The computer-readable storage device of claim 15, wherein the computer-readable storage device stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising:

generating an entry for an adaptation corpus based on the correctness result.

19. The computer-readable storage device of claim 18, wherein adapting operation of the semantic classifier based on the correctness result further comprises adapting operation of the semantic classifier based on the adaptation corpus.

20. The computer-readable storage device of claim 15, wherein determining whether the corresponding label is correct indicates whether the corresponding label attributed by the semantic classifier is one of a correct label and an incorrect label.