Method and system for automatically detecting morphemes in a task classification system using lattices
View Patent ↗In an embodiment, a lattice of phone strings in an input communication of a user may be recognized, wherein the lattice may represent a distribution over the phone strings. Morphemes in the input communication of the user may be detected using the recognized lattice. Task-type classification decisions may be made based on the detected morphemes in the input communication of the user.
1. A method comprising:
receiving verbal speech and non-verbal speech from a user;
selecting verbal candidate morphemes from the verbal speech and non-verbal candidate morphemes from the non-verbal speech;
forming, via a processor, a first lattice, based, at least in part, on the verbal candidate morphemes and stored morphemes, and forming a second lattice based on the non-verbal candidate morphemes;
determining a task objective of the speech, based at least in part on the first lattice and the second lattice; and
routing the user according to the task objective.
2. The method of claim 1 , further comprising:
determining a second task objective of the non-verbal speech, based at least in part on the non-verbal lattice; and
determining if one of the task objective and the second task objective has priority.
3. The method of claim 1 , wherein the non-verbal speech comprises at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.
4. The method of claim 1 , wherein the verbal candidate morphemes are expressed in multimodal form.
5. The method of claim 1 , further comprising prompting the user to provide a feedback response.
6. The method of claim 5 , wherein the feedback response comprises at least one of a confirmation with respect to the task objective and additional information with respect to the speech.
7. The method of claim 1 , wherein the first lattice determines a salience measure associated with the task objective and the verbal candidate morphemes.
8. A system comprising:
a processor; and
a non-transitory computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform a method comprising:
receiving verbal speech and non-verbal speech from a user;
selecting verbal candidate morphemes from the verbal speech and non-verbal candidate morphemes from the non-verbal speech;
forming a first lattice based, at least in part, on the verbal candidate morphemes and stored morphemes, and forming a second lattice based on the non-verbal candidate morphemes;
determining a task objective of the speech, based at least in part on the first lattice and the second lattice; and
routing the user according to the task objective.
9. The system of claim 8 , the instructions, when executed by the processor, cause the processor to perform a method further comprising:
determining a second task objective of the non-verbal speech, based at least in part on the non-verbal lattice; and
determining if one of the task objective and the second task objective has priority.
10. The system of claim 8 , wherein the non-verbal speech comprises at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.
11. The system of claim 8 , wherein the verbal candidate morphemes are expressed in multimodal form.
12. The system of claim 8 , the instructions, when executed by the processor, cause the processor to perform a method further comprising prompting the user to provide a feedback response.
13. The system of claim 12 , wherein the feedback response comprises at least one of a confirmation with respect to the task objective and additional information with respect to the speech.
14. The system of claim 8 , wherein the first lattice determines a salience measure associated with the task objective and the verbal candidate morphemes.
15. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to perform a method comprising:
receiving verbal speech and non-verbal speech from a user;
selecting verbal candidate morphemes from the verbal speech and non-verbal candidate morphemes from the non-verbal speech;
forming a first lattice based, at least in part, on the verbal candidate morphemes and stored morphemes, and forming a second lattice based on the non-verbal candidate morphemes;
determining a task objective of the speech, based at least in part on the first lattice and the second lattice; and
routing the user according to the task objective.
16. The non-transitory computer-readable storage medium of claim 15 , the instructions, when executed by the computing device, cause the computing device to perform a method further comprising:
determining a second task objective of the non-verbal speech, based at least in part on the non-verbal lattice; and
determining if one of the task objective and the second task objective has priority.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the non-verbal speech comprises at least one of gestures, body movements, head movements, non-responses, text, keyboard entries, keypad entries, mouse clicks, DTMF codes, pointers, stylus, cable set-top box entries, graphical user interface entries, and touchscreen entries.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the verbal candidate morphemes are expressed in multimodal form.
19. The non-transitory computer-readable storage medium of claim 15 , the instructions, when executed by the computing device, cause the computing device to perform a method further comprising prompting the user to provide a feedback response.
20. The non-transitory computer-readable storage medium of claim 19 , wherein the feedback response comprises at least one of a confirmation with respect to the task objective and additional information with respect to the speech.