METHOD AND SYSTEM FOR AUTOMATICALLY DETECTING MORPHEMES IN A TASK CLASSIFICATION SYSTEM USING LATTICES

• US 20080288244A1
• Filed: 07/30/2008
• Published: 11/20/2008
• Est. Priority Date: 11/05/1999
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Riccardi, Giuseppe, Wright, Jeremy Huntley, Gorin, Allen Louis, Petrovska-Delacretaz, Dijana
• Granted Patent: US 8,010,361 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G10L 15/08 Speech classification or search

Abstract

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.

Claims

1. A tangible computer-readable medium storing instructions for controlling a computing device to detect morphemes using lattices in an automated task classification system which operates on one or more task objectives of a user, the instructions comprising:

recognizing a lattice of phone strings in user input, the lattice representing a distribution over the phone strings;

detecting morphemes in the user input using the recognized lattice; and

making task-type classification decisions based on the detected morphemes in the user input.

2. The tangible computer-readable medium of claim 1, wherein the morphemes include at least one of verbal speech or non-verbal speech.

3. The tangible computer-readable medium of claim 2, wherein the non-verbal speech includes use of 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 or touchscreen entries.

4. The tangible computer-readable medium of claim 1, wherein the morphemes are expressed in multimodal form.

5. The tangible computer-readable medium of claim 1, wherein the user input is derived from the verbal and non-verbal speech and an environment of the user.

6. The tangible computer-readable medium of claim 1, wherein the morphemes in the input communication of the user are derived from actions of the user, including a focus of attention of the user.

7. The tangible computer-readable medium of claim 1, wherein the instructions further comprise prompting the user to provide a feedback response including additional information with respect to an initial user input.

8. The tangible computer-readable medium of claim 1, wherein the instructions further comprise prompting the user to provide a feedback response that includes a confirmation with respect to at least one of the task objectives determined in the classification decision.

9. The tangible computer-readable medium of claim 1, wherein the user input is routed based on a respective one of the classification decisions.

10. The tangible computer-readable medium of claim 1, wherein the classification decisions and corresponding user input are collected for automated learning purposes.

11. The tangible computer-readable medium of claim 1, wherein a relationship between the detected morphemes and the one or more task objectives includes a salience measure of one of the detected morphemes with respect to a specified one of a plurality of predetermined task objectives.

12. The tangible computer-readable medium of claim 11, wherein the salience measure is represented as a conditional probability of one of the one or more task objectives being requested given an appearance of the morpheme in the user input, the conditional probability being a highest value in a distribution of the conditional probabilities over the plurality of predetermined task objectives.

13. The tangible computer-readable medium of claim 11, wherein each of the plurality of detected morphemes has a salience measure exceeding a predetermined threshold.

14. The tangible computer-readable medium of claim 1, wherein a relationship between the detected morphemes and a predetermined set of task objectives includes a mutual information measure within a language of the morphemes.

15. The tangible computer-readable medium of claim 14, wherein each of the detected morphemes has a mutual information measure exceeding a predetermined threshold.

16. The tangible computer-readable medium of claim 1, wherein the user input represents a request for at least one of the set of predetermined task objectives.

17. The tangible computer-readable medium of claim 2, wherein each of the verbal and non-verbal speech is directed to a respective one of the one or more task objectives and each of the verbal and non-verbal speech is labeled with the respective one of the one or more task objectives to which it is directed.

18. The tangible computer-readable medium of claim 1, wherein the instructions further comprise:

generating morphemes by clustering selected ones of semantically and syntactically similar salient sub-morphemes from training speech; and

storing the generated morphemes in a database which is used to detect morphemes in the recognized lattice.

19. A tangible computer-readable medium storing instructions for controlling a computing device to perform task classification which operates on one or more task objectives of a user, the instructions comprising:

selecting salient phone-phrases from training speech;

generating morphemes by clustering selected ones of the salient phone-phrases which are semantically and syntactically similar;

recognizing a lattice of phone strings in user input, the lattice representing a distribution over the phone strings;

detecting morphemes in the user input using the recognized lattice; and

making task-type classification decisions based on the detected morphemes in the user input.

20. A tangible computer-readable medium storing instructions for controlling a computing device to perform task classification using morphemes which operate on a task objective of a user, the morphemes being generated by clustering selected ones of silent sub-morphemes or salient phone phrases from training speech which are semantically and syntactically similar, the instructions comprising:

detecting morphemes present in user input by utilizing an input speech recognizer, the user input including verbal speech from the user; and

making task-type classification decisions based on the detected morphemes in the user input, wherein the input speech recognizer detects the morphemes present in the user input.