System and method of spoken language understanding in human computer dialogs
View Patent ↗A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify.
1. A method comprising:
partitioning, via a processor, a speech recognizer output into independent clauses;
identifying, independent of domain, a dialog act for each of the independent clauses;
identifying, dependent on domain, an object within each of the independent clauses; and
recursively generating, for each independent clause in the independent clauses, a semantic representation using the dialog act and the object of each independent clause.
2. The method of claim 1 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.
3. The method of claim 1 , further comprising:
identifying, dependent on domain, an action within each of the independent clauses, wherein recursively generating the semantic representation further comprises using the action.
4. The method of claim 1 , wherein while recursively generating the semantic representation, additional objects are extracted from each of the independent clauses.
5. The method of claim 1 , wherein identifying the object comprises using a domain specific classifier.
6. The method of claim 1 , wherein recursively generating the semantic representation further comprises identifying relationships between the dialog act and the object.
7. The method of claim 1 , wherein recursively generating the semantic representation further comprises filling in a predefined data structure associated with the dialog act.
8. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising:
partitioning, via a processor, a speech recognizer output into independent clauses;
identifying, independent of domain, a dialog act for each of the independent clauses;
identifying, dependent on domain, an object within each of the independent clauses; and
recursively generating, for each independent clause in the independent clauses, a semantic representation using the dialog act and the object of each independent clause.
9. The system of claim 8 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.
10. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising:
identifying, dependent on domain, an action within each of the independent clauses, wherein recursively generating the semantic representation further comprises using the action.
11. The system of claim 8 , wherein while recursively generating the semantic representation, additional objects are extracted from each of the independent clauses.
12. The system of claim 8 , wherein identifying the object comprises using a domain specific classifier.
13. The system of claim 8 , wherein recursively generating the semantic representation further comprises identifying relationships between the dialog act and the object.
14. The system of claim 8 , wherein recursively generating the semantic representation further comprises filling in a predefined data structure associated with the dialog act.
15. A computer-readable storage medium having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:
partitioning, via a processor, a speech recognizer output into independent clauses;
identifying, independent of domain, a dialog act for each of the independent clauses;
identifying, dependent on domain, an object within each of the independent clauses; and
recursively generating, for each independent clause in the independent clauses, a semantic representation using the dialog act and the object of each independent clause.
16. The computer-readable storage medium of claim 15 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.
17. The computer-readable storage medium of claim 15 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising:
identifying, dependent on domain, an action within each of the independent clauses, wherein recursively generating the semantic representation further comprises using the action.
18. The computer-readable storage medium of claim 15 , wherein while recursively generating the semantic representation, additional objects are extracted from each of the independent clauses.
19. The computer-readable storage medium of claim 15 , wherein identifying the object comprises using a domain specific classifier.
20. The computer-readable storage medium of claim 15 , wherein recursively generating the semantic representation further comprises identifying relationships between the dialog act and the object.