Multitask learning for spoken language understanding
View Patent ↗Systems for improving or generating a spoken language understanding system using a multitask learning method for intent or call-type classification. The multitask learning method aims at training tasks in parallel while using a shared representation. A computing device automatically re-uses the existing labeled data from various applications, which are similar but may have different call-types, intents or intent distributions to improve the performance. An automated intent mapping algorithm operates across applications. In one aspect, active learning is employed to selectively sample the data to be re-used.
1. A method comprising:
mapping, via one or more processors, call-types between a first spoken dialog system and a second spoken dialog system using a set of labeled data, to yield mapped call-types;
training, via the one or more processors, a model using information based on the mapped call-types; and
routing incoming calls based on the model.
2. The method of claim 1 , wherein the mapping of the call-types comprises performing one of splitting the call-types, merging the call-types, and renaming the call-types.
3. The method of claim 2 , wherein the merging of the call-types comprises cross-labeling utterances from a dialog using the model.
4. The method of claim 1 , wherein the mapping is further performed using a first training model for the first spoken dialog system and a second training model for the second spoken dialog system.
5. The method of claim 1 , further comprising labeling, as a new call-type, a call-type of the first spoken dialog system when the call-type has more than a specified ratio among the call-types.
6. The method of claim 1 , wherein training the model further comprises active learning to selectively sample data used for the training.
7. The method of claim 6 , wherein selectively sampled data is reused during training.
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:
mapping call-types between a first spoken dialog system and a second spoken dialog system using a set of labeled data, to yield mapped call-types;
training a model using information based on the mapped call-types; and
routing incoming calls based on the model.
9. The system of claim 8 , wherein the mapping of the call-types comprises performing one of splitting the call-types, merging the call-types, and renaming the call-types.
10. The system of claim 9 , wherein the merging of the call-types comprises cross-labeling utterances from a dialog using the model.
11. The system of claim 10 , wherein the mapping is further performed using a first training model for the first spoken dialog system and a second training model for the second spoken dialog system.
12. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in operations comprising labeling, as a new call-type, a call-type of the first spoken dialog system when the call-type has more than a specified ratio among the call-types.
13. The system of claim 8 , wherein training the model further comprises active learning to selectively sample data used for the training.
14. The system of claim 13 , wherein selectively sampled data is reused during training.
15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
mapping call-types between a first spoken dialog system and a second spoken dialog system using a set of labeled data, to yield mapped call-types;
training a model using information based on the mapped call-types; and
routing incoming calls based on the model.
16. The computer-readable storage device of claim 15 , wherein the mapping of the call-types comprises performing one of splitting the call-types, merging the call-types, and renaming the call-types.
17. The computer-readable storage device of claim 16 , wherein the merging of the call-types comprises cross-labeling utterances from a dialog using the model.
18. The computer-readable storage device of claim 17 , wherein the mapping is further performed using a first training model for the first spoken dialog system and a second training model for the second spoken dialog system.
19. The computer-readable storage device of claim 15 , having additional instructions stored which result in operations comprising labeling, as a new call-type, a call-type of the first spoken dialog system when the call-type has more than a specified ratio among the call-types.
20. The computer-readable storage device of claim 15 , wherein training the model further comprises active learning to selectively sample data used for the training.