Relevance recognition for a human machine dialog system contextual question answering based on a normalization of the length of the user input

• US 8,639,517 B2
• Filed: 06/15/2012
• Issued: 01/28/2014
• Est. Priority Date: 03/03/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Di Fabbrizio, Giuseppe, Feng, Junlan
• Primary Examiner(s): Smits, Talivaldis Ivars
• Assistant Examiner(s): Kazeminezhad, Farzad
• Application Number:
  US13/524,714
• Publication Number:
  US 20120253825A1
• Time in Patent Office: 592 Days
• Field of Search: 704/277, 704/256
• US Class Current: 704/275
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/142 Hidden Markov Models [HMMs]
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Disclosed are systems, methods and computer-readable media for controlling a computing device to provide contextual responses to user inputs. The method comprises receiving a user input, generating a set of features characterizing an association between the user input and a conversation context based on at least a semantic and syntactic analysis of user inputs and system responses, determining with a data-driven machine learning approach whether the user input begins a new topic or is associated with a previous conversation context and if the received question is associated with the existing topic, then generating a response to the user input using information associated with the user input and any previous user input associated with the existing topic, based on a normalization of the length of the user input.

Claims

1. A method comprising:

generating, via a processor, a set of features characterizing an association between a user input and a conversation context using prior user inputs;

determining, by normalizing a length of the user input to a previous input in the prior user inputs and using a data-driven machine learning approach, whether the user input is associated with an existing topic related to a previous conversation context; and

when the user input is associated with the existing topic, generating a response to the user input using information associated with the user input and content associated with any previous user input on the existing topic.

2. The method of claim 1, wherein generating the response to the user input further comprises using a model trained for context fusion.

3. The method of claim 1, wherein the data-driven machine learning approach is applied using one of a decision tree, Adaboost, Support Vector Machines, and Maxent.

4. The method of claim 1, wherein the user input is a natural language request.

5. The method of claim 1, further comprising classifying the prior user inputs based on context space.

6. The method of claim 1, wherein generating the response to the user input further comprises an information fusion of the user input and the previous user input.

7. The method of claim 1, wherein generating the set of features further comprises using a semantic and syntactic analysis of the user input and the prior user inputs.

8. The method of claim 1, wherein determining whether the user input is associated with the existing topic related to the previous conversation context further comprises comparing semantic similarity information of a normalized feature and a non-normalized feature.

9. A system comprising:

a processor; and

a computer-readable storage medium storing instructions which, when executed on a processor, cause the processor to perform operations comprising;

generating a set of features characterizing an association between a user input and a conversation context using prior user inputs;

determining, by normalizing a length of the user input to a previous input in the prior user inputs and using a data-driven machine learning approach, whether the user input is associated with an existing topic related to a previous conversation context; and

when the user input is associated with the existing topic, generating a response to the user input using information associated with the user input and content associated with any previous user input on the existing topic.

10. The system of claim 9, wherein generating the response to the user input further comprises using a model trained for context fusion.

11. The system of claim 9, wherein the data-driven machine learning approach is applied using one of a decision tree, Adaboost, Support Vector Machines, and Maxent.

12. The system of claim 9, wherein the user input is a natural language request.

13. The system of claim 9, the computer-readable storage medium having additional instructions stored which result in the operations further comprising classifying the prior user inputs based on context space.

14. The system of claim 9, wherein generating the response to the user input further comprises an information fusion of the user input and the previous user input.

15. The system of claim 9, wherein generating the set of features further comprises using a semantic and syntactic analysis of the user input and the prior user inputs.

16. The system of claim 9, wherein determining whether the user input is associated with the existing topic related to the previous conversation context further comprises comparing semantic similarity information of a normalized feature and a non-normalized feature.

17. A computer-readable storage device having instructions stored which, when executed on a processor, cause the processor to perform operations comprising:

generating a set of features characterizing an association between a user input and a conversation context using prior user inputs;

determining, by normalizing a length of the user input to a previous input in the prior user inputs and using a data-driven machine learning approach, whether the user input is associated with an existing topic related to a previous conversation context; and

when the user input is associated with the existing topic, generating a response to the user input using information associated with the user input and content associated with any previous user input on the existing topic.

18. The computer-readable storage device of claim 17, wherein generating the response to the user input further comprises using a model trained for context fusion.

19. The computer-readable storage device of claim 17, wherein the data-driven machine learning approach is applied using one of a decision tree, Adaboost, Support Vector Machines, and Maxent.

20. The computer-readable storage device of claim 17, wherein the user input is a natural language request.