Automatic generation and display of context, missing attributes and suggestions for context dependent questions in response to a mouse hover on a displayed term

• US 10,366,160 B2
• Filed: 09/30/2016
• Issued: 07/30/2019
• Est. Priority Date: 09/30/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Castelli, Vittorio, Qian, Leiming R., Syed, Zareen S.
• Primary Examiner(s): Kazeminezhad, Farzad
• Application Number:
  US15/282,970
• Publication Number:
  US 20180095947A1
• Time in Patent Office: 1,033 Days
• Field of Search: 704 9, 704235, 455566
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

A method and system are provided for assisting users in a conversation. The method includes identifying concepts in the conversation. The method further includes linking identified concepts in the conversation by matching the identified concepts in the conversation to concepts in a knowledge base. The method also includes generating and displaying on the display device, one or more context dependent suggestions for the conversation based on attributes and values associated with the linked concepts in the knowledge base.

Claims

1. A computer-implemented method for assisting users in a conversation, comprising:

identifying concepts in the conversation;

linking identified concepts in the conversation by matching the identified concepts in the conversation to concepts in a knowledge base; and

generating and displaying on a display device, one or more domain and language independent user-specific context dependent suggestions for discussion questions for the conversation based on attributes and values associated with the linked concepts in the knowledge base by automatically disambiguating concepts identified as important, and inferring missing attributes for the matching concepts in the knowledge base based on additional attributes present in sibling concepts in a taxonomy in the knowledge base,

wherein the context-dependent suggestions for discussion questions are automatically generated and presented to one or more of the particular users in real-time using a personalized interface of the display device, the context-dependent suggestions including one or more suggestions for discussion questions generated based on the inferred missing attributes, and

wherein important topics not explicitly mentioned in the conversation are identified, presented, and highlighted in real-time to aid the users during the conversation in response to a user mouse hover or click on a displayed term.

2. The computer-implemented method of claim 1, further comprising retrieving and displaying on a display device, the attributes and the values associated with the linked concepts in the knowledge base.

3. The computer-implemented method of claim 2, wherein the attributes and values are displayed as information boxes in articles.

4. The computer-implemented method of claim 2, wherein said retrieving and displaying step comprises personalizing the attributes and values with respect to the user based on questions asked by a conversation participant having a particular role.

5. The computer-implemented method of claim 2, wherein said retrieving and displaying step comprises personalizing the attributes and values with respect to the user based on questions asked by other conversation participants about identical or similar concepts.

6. The computer-implemented method of claim 2, wherein said retrieving and displaying step comprises displaying at least one related attribute to the matching concepts in the knowledge base, wherein the at least one related attribute is unmentioned in the conversation.

7. The computer-implemented method of claim 2, further comprising displaying a concept definition on the display device responsive to a user action.

8. The computer-implemented method of claim 1, wherein the concepts in the conversation are identified based on n-grams extracted from the conversation.

9. The computer-implemented method of claim 1, wherein the concepts in the conversation are identified based on conversation features precomputed with respect to an externally accessible knowledge source.

10. The computer-implemented method of claim 1, wherein the concepts in the conversation are identified based on frequency-dependent conversation features and keyword probabilities.

11. The computer-implemented method of claim 1, further comprising disambiguating the concepts, prior to said linking step, and wherein the concepts are disambiguated using disambiguation features selected from a group consisting of a text similarity between a conversation context and a target concept context in the knowledge base, a link probability, and a link popularity feature.

12. The computer-implemented method of claim 1, further comprising computing additional attributes based on inter-article links in the knowledge base.

13. The method of claim 1, further comprising ranking the attributes using an attribute scoring scheme.

14. The computer-implemented method of claim 1, wherein the one or more context dependent suggestions are for follow up questions for the conversation.

15. The computer-implemented method of claim 1, wherein software is provided as a service in a cloud environment to generate and display the one or more context dependent suggestions.

16. A non-transitory computer program product for assisting users in a conversation, the computer program product comprising a computer readable storage medium having computer readable program instructions embodied therewith, the computer readable program instructions executable by a computer to cause the computer to perform a method comprising:

identifying concepts in the conversation;

linking identified concepts in the conversation by matching the identified concepts in the conversation to concepts in a knowledge base; and

generating and displaying on a display device, one or more domain and language independent user-specific context dependent suggestions for discussion questions for the conversation based on attributes and values associated with the linked concepts in the knowledge base by automatically disambiguating concepts identified as important, and inferring missing attributes for the matching concepts in the knowledge base based on additional attributes present in sibling concepts in a taxonomy in the knowledge base,

wherein context-dependent follow-up questions for attributes with missing information are automatically generated and presented to a particular user in real-time responsive to the particular user clicking on a particular attribute with missing information using a personalized, interactive interface of the display device, and

wherein important topics not explicitly mentioned in the conversation are identified, presented, and highlighted in real-time to aid the particular user during the conversation in response to a user mouse hover or click on a displayed term.

17. A system for assisting users in a conversation, comprising:

a computing device having a processor device and a memory operably coupled to the processor, the computing device being configured to;

identify concepts in the conversation;

linking identified concepts in the conversation by matching the identified concepts in the conversation to concepts in a knowledge base; and

generate and display on a display device, one or more domain and language independent user-specific context dependent suggestions for discussion questions for the conversation based on attributes and values associated with the linked concepts in the knowledge base by automatically disambiguating concepts identified as important, and inferring missing attributes for the matching concepts in the knowledge base based on additional attributes present in sibling concepts in a taxonomy in the knowledge base,

wherein context-dependent follow-up questions for attributes with missing information are automatically generated and presented to a particular user in real-time responsive to the particular user clicking on a particular attribute with missing information using a personalized, interactive interface of the display device, and

wherein important topics not explicitly mentioned in the conversation are identified, presented, and highlighted in real-time to aid the user during the conversation in response to a user mouse hover or click on a displayed term.

18. The system of claim 17, wherein the system is configured using a cloud configuration.