System and Method for Generating Natural Language Phrases From User Utterances in Dialog Systems

• US 20100057463A1
• Filed: 08/27/2008
• Published: 03/04/2010
• Est. Priority Date: 08/27/2008
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Cao, Junkuo, Stoia, Laura, Weng, Fuliang, Feng, Zhe, Hu, Junling
• Granted Patent: US 8,874,443 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Embodiments of a dialog system that employs a corpus-based approach to generate responses based on a given number of semantic constraint-value pairs are described. The system makes full use of the data from the user input to produce dialog system responses in combination with a template generator. The system primarily utilizes constraint values in order to realize efficiencies based on the more frequent tasks performed in real dialog systems although rhetorical or discourse aspects of the dialog could also be included in a similar way, that is, labeling the data with such information and performing a training process. The benefits of this system include higher quality user-aligned responses, broader coverage, faster response time, and shorter development cycles.

Claims

1. A method of generating responses in a dialog system in response to user input in a current conversation session, comprising:

collecting original user phrase data from one or more conversation sessions between the user and the dialog system or other offline sources;

extracting one or more constraints, each comprising a constraint-value pair, from the user input;

generalizing the extracted constraints into phrase patterns to produce general phrase patterns;

constructing a response database consisting of the original phrase data and the general phrase patterns;

transmitting a set of filled constraints to a response generator component from the user input; and

selecting at least one phrase from the response database that optimally matches the set of filled constraints.

2. The method of claim 1 wherein the one or more conversation sessions comprises the current session including the user input.

3. The method of claim 2 further comprising:

utilizing a chunking-based approach is used to extract phrases used by the user in a constraint specification; and

updating the extracted phrases with values retrieved from the response database.

4. The method of claim 1 wherein the one or more conversation sessions comprises at least one previous session not including the current session user input.

5. The method of claim 4 further comprising:

utilizing one of a parse-tree based approach or a chunking-based approach to extract phrases used by the user in a constraint specification and form a pool of examples of how to lexicalize constraints in the user input; and

generalizing the constraints into phrase patterns by replacing constraints with corresponding semantic class names.

6. The method of claim 5 wherein the parse-tree based approach structurally annotates all user utterances as parse-trees.

7. The method of claim 5 wherein the chunking-based approach tags all user utterances using a part-of-speech tagger, and parsed by one of a shallow parser or deep structure parser.

8. The method of claim 1 further comprising:

determining whether or not the constraint and value pairs of the filled constraints are present in the response database; and

configuring the response generator to use the corresponding phrase in the response database if the constraint and value pairs of the filled constraints are present in the response database.

9. The method of claim 1 further comprising:

determining whether or not the constraint and value pairs of the filled constraints are present in the response database; and

configuring the response generator to use a corresponding phrase in the response database that overlaps the user input constraint and value pairs of the filled constraints to as high a degree if possible, if the values of the constraints are different between the filled constraints of the database and the values of the constraints in the user input.

10. The method of claim 1 further comprising:

determining whether or not the constraint and value pairs of the filled constraints are present in the response database; and

creating constraint patterns from existing or generated patterns if the constraint and value pairs of the filled constraints are not present in the response database.

11. The method of claim 1 wherein the user input comprises a single turn in a conversation session consisting of multiple dialog turns between the user and the dialog system.

18. The method of claim 1 further comprising:

utilizing a chunking-based approach is used to extract phrases used by the user in a constraint specification; and

updating the extracted phrases with values retrieved from the response database.

12. A method of generating phrases in a dialog system in response to user input during one or more turns of a present conversation session between the user and the dialog system, comprising:

collecting a corpus of user data from one or more conversation sessions between the user and the dialog system;

constructing phrase models based on the corpus of user data, wherein the phrase models comprise constraint sets consisting of constraint-value pairs;

selecting an optimal constraint set from the corpus of user data in response to a constraint within the user input; and

generating a sentence for output from a response generator incorporating the optimal constraint set.

13. The method of claim 12 wherein the step of constructing phrase models further comprises:

identifying phrase expressions from user utterances that have constraints;

generalizing identified constraints through a decomposition process; and

creating one or more default phrase expressions for each constraint set.

14. The method of claim 12 wherein the step of selecting an optimal constraint set further comprises:

determining whether or not the constraint and value pairs of the filled constraints are present in the response database;

configuring the response generator to use the corresponding phrase in the response database if the constraint and value pairs of the filled constraints are present in the response database;

configuring the response generator to use a corresponding phrase in the response database that overlaps the user input constraint and value pairs of the filled constraints to as high a degree if possible, if the values of the constraints are different between the filled constraints of the database and the values of the constraints in the user input; and

creating constraint patterns from existing or generated patterns if the constraint and value pairs of the filled constraints are not present in the response database.

15. The method of claim 12 wherein the user input comprises one or more sentences, each sentence consisting of a triple comprising a speech act, an action, and a constraint set, and wherein the step of generating a sentence for output from a response generator further comprises:

indexing each sentence of the user input into a corresponding triple;

splitting the constraint set of the triple into a plurality of smaller subsets if the triple is not present in the corpus;

generating a sequence of triples from the split step;

generate a corresponding sentence for each triple of the sequence of triples based on a defined training model; and

reducing redundancies in the generated corresponding sentences.

16. The method of claim 15 wherein the step of reducing redundancies further comprises:

determining if a noun phrase used in a current sentence is also used in a previous sentence and refers to an identical entity; and

replacing the current noun phrase with a pronoun with the same number, person, and gender if the noun phrase is used in the previous sentence.

17. The method of claim 12 wherein the corpus of user data from one or more conversation sessions includes the current session including the user input.

19. The method of claim 12 wherein the corpus of user data from one or more conversation sessions conversation sessions comprising at least one previous session not including the current session user input.

20. The method of claim 19 further comprising:

utilizing one of a parse-tree based approach or a chunking-based approach to extract phrases used by the user in a constraint specification and form a pool of examples of how to lexicalize constraints in the user input; and

generalizing the constraints into phrase patterns by replacing constraints with corresponding semantic class names.

21. The method of claim 20 wherein the parse-tree based approach structurally annotates all user utterances as parse-trees.

22. The method of claim 20 wherein the chunking-based approach tags all user utterances using a part-of-speech tagger, and parsed by one of a shallow parser or deep structure parser.