SYSTEM AND METHOD FOR DIALOG MODELING

• US 20100131274A1
• Filed: 11/26/2008
• Published: 05/27/2010
• Est. Priority Date: 11/26/2008
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Bangalore, Srinivas, Stent, Amanda
• Granted Patent: US 9,129,601 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 40/12 Use of codes for handling textual entities
• CPC Class Codes: G06F 40/137 Hierarchical processing, e.g. outlines
• CPC Class Codes: G06F 40/154 Tree transformation for tree-structured or markup documents, e.g. XSLT, XSL-FO or stylesheets
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0638 Interactive procedures
• CPC Class Codes: G10L 25/12 the extracted parameters being prediction coefficients

Abstract

Disclosed herein are systems, computer-implemented methods, and computer-readable media for dialog modeling. The method includes receiving spoken dialogs annotated to indicate dialog acts and task/subtask information, parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs, and constructing a functional task structure of the parsed spoken dialogs. The method can further either interpret user utterances with the functional task structure of the parsed spoken dialogs or plan system responses to user utterances with the functional task structure of the parsed spoken dialogs. The parse-based dialog model can be a shift-reduce model, a start-complete model, or a connection path model.

Claims

1. A computer-implemented method of dialog modeling, the method comprising:

receiving spoken dialogs annotated to indicate dialog acts and task/subtask information;

parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs; and

constructing a functional task structure of the parsed spoken dialogs.

2. The computer-implemented method of claim 1, wherein the parse-based dialog model is a shift-reduce model having a stack and a tree which (a) shifts each utterance onto the stack, (b) inspects the stack, and (c) based on the stack inspection, performs a reduce action that creates subtrees in the tree.

3. The computer-implemented method of claim 1, wherein the parse-based dialog model is a start-complete model which uses a stack to maintain a global parse state and produces a dialog task structure directly without producing an equivalent tree.

4. The computer-implemented method of claim 1, wherein the parse-based dialog model is a connection path model which does not use a stack to maintain a global parse state, and wherein the connection path model (a) directly predicts a connection path from a root to a terminal for each received spoken dialog, and (b) creates a parse tree representing the connection path for each received spoken dialog.

5. The computer-implemented method of claim 1, the method further comprising:

incrementally receiving user utterances as a dialog progresses;

assigning a dialog act to a current user utterance based on the functional task structure of the parsed spoken dialogs;

assigning a subtask label to the current user utterance based on the functional task structure of the parsed spoken dialogs;

predicting a system subtask label for a next system utterance based on the functional task structure of the parsed spoken dialogs;

predicting a system dialog act for a next system utterance based on the functional task structure of the parsed spoken dialogs;

predicting a next subtask label for a next user utterance based on the functional task structure of the parsed spoken dialogs; and

predicting a next dialog act for a next user utterance based on the functional task structure of the parsed spoken dialogs.

6. The computer-implemented method of claim 5, wherein interpreting and predicting are modeled as maximum entropy classifiers which select dialog acts or subtask labels from a pre-selected list.

7. The computer-implemented method of claim 5, the method further comprising measuring dialog efficiency at different dialog stages.

8. A system for dialog modeling, the system comprising:

a module configured to receive spoken dialogs annotated to indicate dialog acts and task/subtask information;

a module configured to parse the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs; and

a module configured to construct a functional task structure of the parsed spoken dialogs.

9. The system of claim 8, wherein the parse-based dialog model is a shift-reduce model having a stack and a tree which (a) shifts each utterance onto the stack, (b) inspects the stack, and (c) based on the stack inspection, performs a reduce action that creates subtrees in the tree.

10. The system of claim 8, wherein the parse-based dialog model is a start-complete model which uses a stack to maintain a global parse state and produces a dialog task structure directly without producing an equivalent tree.

11. The system of claim 8, wherein the parse-based dialog model is a connection path model which does not use a stack to maintain a global parse state, and wherein the connection path model (a) directly predicts a connection path from a root to a terminal for each received spoken dialog, and (b) creates a parse tree representing the connection path for each received spoken dialog.

12. The system of claim 8, the system further comprising:

a module configured to incrementally receive user utterances as a dialog progresses;

a module configured to assign a dialog act to a current user utterance based on the functional task structure of the parsed spoken dialogs;

a module configured to assign a subtask label to the current user utterance based on the functional task structure of the parsed spoken dialogs;

a module configured to predict a system subtask label for a next system utterance based on the functional task structure of the parsed spoken dialogs;

a module configured to predict a system dialog act for a next system utterance based on the functional task structure of the parsed spoken dialogs;

a module configured to predict a next subtask label for a next user utterance based on the functional task structure of the parsed spoken dialogs; and

a module configured to predict a next dialog act for a next user utterance based on the functional task structure of the parsed spoken dialogs.

13. The system of claim 12, the system further comprising a module configured to model predictions as maximum entropy classifiers which select dialog acts or subtask labels from a pre-selected list.

14. The system of claim 12, the system further comprising a module configured to measure dialog efficiency at different dialog stages.

15. A tangible computer-readable medium storing a computer program having instructions for dialog modeling, the instructions comprising:

receiving spoken dialogs annotated to indicate dialog acts and task/subtask information;

parsing the spoken dialogs with a hierarchical, parse-based dialog model which operates incrementally from left to right and which only analyzes a preceding dialog context to generate parsed spoken dialogs; and

constructing a functional task structure of the parsed spoken dialogs.

16. The tangible computer-readable medium of claim 15, wherein the parse-based dialog model is a shift-reduce model having a stack and a tree which (a) shifts each utterance onto the stack, (b) inspects the stack, and (c) based on the stack inspection, performs a reduce action that creates subtrees in the tree.

17. The tangible computer-readable medium of claim 15, wherein the parse-based dialog model is a start-complete model which uses a stack to maintain a global parse state and produces a dialog task structure directly without producing an equivalent tree.

18. The tangible computer-readable medium of claim 15, wherein the parse-based dialog model is a connection path model which does not use a stack to maintain a global parse state, and wherein the connection path model (a) directly predicts a connection path from a root to a terminal for each received spoken dialog, and (b) creates a parse tree representing the connection path for each received spoken dialog.

19. The tangible computer-readable medium of claim 15, the instructions further comprising:

incrementally receiving user utterances as a dialog progresses;

assigning a dialog act to a current user utterance based on the functional task structure of the parsed spoken dialogs;

assigning a subtask label to the current user utterance based on the functional task structure of the parsed spoken dialogs;

predicting a system subtask label for a next system utterance based on the functional task structure of the parsed spoken dialogs;

predicting a system dialog act for a next system utterance based on the functional task structure of the parsed spoken dialogs;

predicting a next subtask label for a next user utterance based on the functional task structure of the parsed spoken dialogs; and

predicting a next dialog act for a next user utterance based on the functional task structure of the parsed spoken dialogs.

20. The tangible computer-readable medium of claim 19, the instructions further comprising measuring dialog efficiency at different dialog stages.