User intention based on N-best list of recognition hypotheses for utterances in a dialog
View Patent ↗Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for using alternate recognition hypotheses to improve whole-dialog understanding accuracy. The method includes receiving an utterance as part of a user dialog, generating an N-best list of recognition hypotheses for the user dialog turn, selecting an underlying user intention based on a belief distribution across the generated N-best list and at least one contextually similar N-best list, and responding to the user based on the selected underlying user intention. Selecting an intention can further be based on confidence scores associated with recognition hypotheses in the generated N-best lists, and also on the probability of a user's action given their underlying intention. A belief or cumulative confidence score can be assigned to each inferred user intention.
1. A method comprising:
receiving, as part of a spoken dialog with a spoken dialog system, a user utterance;
generating, via a processor, a plurality of recognition hypothesis; and
selecting an underlying user intention based on an analysis of confidence scores, wherein the analysis of confidence scores sums confidence scores over all possible hidden user actions associated with the plurality of recognition hypothesis, wherein the hidden user actions are not observable by the spoken dialog system.
2. The method of claim 1 , further comprising:
assigning an individual confidence score to each recognition hypothesis in the plurality of recognition hypothesis.
3. The method of claim 1 , wherein confidence scores are operative over a whole dialog.
4. The method of claim 1 , wherein the underlying user intention is further based on a probability of a user action.
5. The method of claim 1 , wherein the user utterance is received during a dialog turn.
6. The method of claim 1 , wherein the all possible hidden user actions form a hidden Markov model.
7. The method of claim 1 , further comprising responding to the user utterance based on the underlying user intention.
8. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed on the processor, cause the processor to perform operations comprising:
receiving, as part of a spoken dialog with a spoken dialog system, a user utterance;
generating, via a processor, a plurality of recognition hypothesis; and
selecting an underlying user intention based on an analysis of confidence scores, wherein the analysis of confidence scores sums confidence scores over all possible hidden user actions associated with the plurality of recognition hypothesis, wherein the hidden user actions are not observable by the spoken dialog system.
9. The system of claim 8 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising:
assigning an individual confidence score to each recognition hypothesis in the plurality of recognition hypothesis.
10. The system of claim 9 , wherein confidence scores are operative over a whole dialog.
11. The system of claim 9 , wherein the underlying user intention is further based on a probability of a user action.
12. The system of claim 9 , wherein the user utterance is received during a dialog turn.
13. The system of claim 9 , wherein the all possible hidden user actions form a hidden Markov model.
14. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising responding to the user utterance based on the underlying user intention.
15. A non-transitory computer-readable storage device having instructions stored which, when executed on a computing device, cause the computing device to perform operations comprising:
receiving, as part of a spoken dialog with a spoken dialog system, a user utterance;
generating, via a processor, a plurality of recognition hypothesis; and
selecting an underlying user intention based on an analysis of confidence scores, wherein the analysis of confidence scores sums confidence scores over all possible hidden user actions associated with the plurality of recognition hypothesis, wherein the hidden user actions are not observable by the spoken dialog system.
16. The non-transitory computer-readable storage device of claim 15 , having additional comprising:
assigning an individual confidence score to each recognition hypothesis in the plurality of recognition hypothesis.
17. The non-transitory computer-readable storage device of claim 15 , wherein confidence scores are operative over a whole dialog.
18. The non-transitory computer-readable storage device of claim 15 , wherein the underlying user intention is further based on a probability of a user action.
19. The non-transitory computer-readable storage device of claim 15 , wherein the user utterance is received during a dialog turn.
20. The non-transitory computer-readable storage device of claim 15 , wherein the all possible hidden user actions form a hidden Markov model.