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 speech recognizer output into a plurality of independent clauses; and
for an independent clause in the plurality of independent clauses:
identifying an object; and
recursively generating, via a processor, for each sub-independent clause within the independent clause, a semantic representation using the object.
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 , wherein the object comprises a domain-dependent object.
4. The method of claim 1 , further comprising:
identifying, in a domain-dependent manner, an action within the independent clause, wherein recursively generating the semantic representation further comprises using the action.
5. The method of claim 1 , wherein while recursively generating the semantic representation, additional objects are extracted from the independent clause.
6. The method of claim 1 , wherein identifying the object comprises using a domain specific classifier.
7. The method of claim 1 , wherein recursively generating the semantic representation further comprises identifying relationships between a dialog act in the independent clause and the object.
8. The method of claim 1 , wherein recursively generating the semantic representation further comprises filling in a data structure associated with a dialog act in the independent clause.
9. A system comprising:
a processor; and
a computer-readable storage device having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
partitioning speech recognizer output into a plurality of independent clauses; and
for an independent clause in the plurality of independent clauses:
identifying an object; and
recursively generating, via a processor, for each sub-independent clause within the independent clause, a semantic representation using the object.
10. The system of claim 9 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.
11. The system of claim 9 , wherein the object comprises a domain-dependent object.
12. The system of claim 9 , further comprising:
identifying, in an domain-dependent manner, an action within the independent clause, wherein recursively generating the semantic representation further comprises using the action.
13. The system of claim 9 , wherein while recursively generating the semantic representation, additional objects are extracted from the independent clause.
14. The system of claim 9 , wherein identifying the object comprises using a domain specific classifier.
15. The system of claim 9 , wherein recursively generating the semantic representation further comprises identifying relationships between a dialog act in the independent clause and the object.
16. The system of claim 9 , wherein recursively generating the semantic representation further comprises filling in a data structure associated with a dialog act in the independent clause.
17. A non-transitory computer-readable storage device having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:
partitioning speech recognizer output into a plurality of independent clauses; and
for an independent clause in the plurality of independent clauses:
identifying an object; and
recursively generating, via a processor, for each sub-independent clause within the independent clause, a semantic representation using the object.
18. The non-transitory computer-readable storage device of claim 17 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.
19. The non-transitory computer-readable storage device of claim 17 , wherein the object comprises a domain-dependent object.
20. The non-transitory computer-readable storage device of claim 17 , further comprising:
identifying, in an domain-dependent manner, an action within the independent clause, wherein recursively generating the semantic representation further comprises using the action.