Private-public context analysis for natural language content disambiguation

• US 9,760,627 B1
• Filed: 05/13/2016
• Issued: 09/12/2017
• Est. Priority Date: 05/13/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bradley, Lisa M. W., Harpur, Liam, Quirk, Aaron J., Sun, Lin
• Primary Examiner(s): Yen, Eric
• Application Number:
  US15/154,162
• Time in Patent Office: 487 Days
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Mechanisms are provided for implementing a natural language content (NLC) disambiguation engine. The NLC disambiguation engine operates to identify, in a corpus of natural language content, a portion of natural language content (NLC) that is determined to be ambiguous with regard to the context of the portion of NLC. The NLC disambiguation engine compares the ambiguous content portion to private content information associated with a source of the ambiguous content portion. The NLC disambiguation engine identifies a domain of the ambiguous content portion based on a domain of a matching portion of the private content information. The NLC disambiguation engine performs a clarifying operation that clarifies the ambiguous content portion based on the identified domain of the matching portion of the private content information to thereby generate a clarified content portion for processing by a cognitive operation of a cognitive system.

Claims

1. A method, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to configure the data processing system to implement a natural language content (NLC) disambiguation engine, the method comprising:

identifying, by the NLC disambiguation engine, in a corpus of natural language content, a portion of natural language content (NLC) that is determined to be ambiguous with regard to a context of the portion of NLC, thereby identifying an ambiguous content portion;

comparing, by the NLC disambiguation engine, the ambiguous content portion to private content information associated with a source of the ambiguous content portion, wherein the private content information is content information accessible to users and resources associated with the source and is not accessible to users or resources that are not associated with the source;

identifying, by the NLC disambiguation engine, a domain of the ambiguous content portion based on a domain of a matching portion of the private content information; and

performing, by the NLC disambiguation engine, a clarifying operation that clarifies the ambiguous content portion based on the identified domain of the ambiguous content portion to thereby generate a clarified content portion for processing by a cognitive operation of a cognitive system.

2. The method of claim 1, wherein identifying the ambiguous content portion comprises determining that the portion of NLC is associated with a flag indicating that at least one user considers the portion of NLC to be ambiguous.

3. The method of claim 1, wherein identifying the ambiguous content portion comprises comparing the natural language content in the corpus of natural language content to one or more patterns of natural language content corresponding to ambiguous content, and identifying the portion of natural language content to be the ambiguous content portion in response to the portion of natural language content matching at least one of the one or more patterns of natural language content.

4. The method of claim 1, wherein comparing the ambiguous content portion to private content information comprises:

comparing one or more extracted first features of the ambiguous content portion to one or more second features of the private content information; and

identifying a matching portion of the private content information based on a degree of correspondence between the one or more extracted first features and the one or more second features, wherein the portion of the private content information comprises a portion having a second feature matching a first feature.

5. The method of claim 1, wherein the clarifying operation comprises at least one of sending a clarifying question to the source, wherein the clarifying question specifies the identified domain of the ambiguous content portion or sending a notification to the source indicating a need to clarify the ambiguous content portion and specifying the identified domain of the ambiguous content portion.

6. The method of claim 1, wherein the domain of the matching portion of the private content information comprises a domain, in a taxonomy data structure specifying domains corresponding to private content information associated with the source, which is indicated by the source to be able to be used by the NLC disambiguation engine to disambiguate ambiguous content.

7. The method of claim 6, wherein the identified domain of the ambiguous content portion is part of a sub-portion of the taxonomy data structure that is registered by the source with the NLC disambiguation engine as being able to be used by the NLC disambiguation engine to disambiguate ambiguous content, and wherein other portions of the taxonomy data structure are not able to be used by the NLC disambiguation engine to disambiguate ambiguous content.

8. The method of claim 1, wherein the private content information is not exposed to users or resources that are not associated with the source or authorized access by the source when performing the method.

9. The method of claim 1, wherein the portion of NLC comprises a portion of natural language content of a corpus of natural language content ingested into a cognitive system, and wherein the cognitive operation is one of a cognitive search operation for searching for matching natural language content to a search request submitted to the cognitive system or a cognitive question answering operation for generating a natural language answer to a input natural language question.

10. The method of claim 1, wherein the portion of NLC comprises a message posted to a collaborative website by a user that is the source, and wherein the private content information comprises a set of messages posted to the collaborative website by users that are part of a private group of the collaborative website.

11. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement a natural language content (NLC) disambiguation engine, that operates to:

identify, in a corpus of natural language content, a portion of natural language content (NLC) that is determined to be ambiguous with regard to a context of the portion of NLC, thereby identifying an ambiguous content portion;

compare the ambiguous content portion to private content information associated with a source of the ambiguous content portion, wherein the private content information is content information accessible to users and resources associated with the source and is not accessible to users or resources that are not associated with the source;

identify a domain of the ambiguous content portion based on a domain of a matching portion of the private content information; and

perform a clarifying operation that clarifies the ambiguous content portion based on the identified domain of the ambiguous content portion to thereby generate a clarified content portion for processing by a cognitive operation of a cognitive system.

12. The computer program product of claim 11, wherein the NLC disambiguation engine identifying the ambiguous content portion comprises determining that the portion of NLC is associated with a flag indicating that at least one user considers the portion of NLC to be ambiguous.

13. The computer program product of claim 11, wherein the NLC disambiguation engine identifying the ambiguous content portion comprises comparing the natural language content in the corpus of natural language content to one or more patterns of natural language content corresponding to ambiguous content, and identifying the portion of natural language content to be the ambiguous content portion in response to the portion of natural language content matching at least one of the one or more patterns of natural language content.

14. The computer program product of claim 11, wherein the NLC disambiguation engine comparing the ambiguous content portion to private content information comprises:

comparing one or more extracted first features of the ambiguous content portion to one or more second features of the private content information; and

identifying a matching portion of the private content information based on a degree of correspondence between the one or more extracted first features and the one or more second features, wherein the portion of the private content information comprises a portion having a second feature matching a first feature.

15. The computer program product of claim 11, wherein the clarifying operation comprises at least one of sending a clarifying question to the source, wherein the clarifying question specifies the identified domain of the ambiguous content portion or sending a notification to the source indicating a need to clarify the ambiguous content portion and specifying the identified domain of the ambiguous content portion.

16. The computer program product of claim 11, wherein the domain of the matching portion of the private content information comprises a domain, in a taxonomy data structure specifying domains corresponding to private content information associated with the source, which is indicated by the source to be able to be used by the NLC disambiguation engine to disambiguate ambiguous content.

17. The computer program product of claim 16, wherein the identified domain of the ambiguous content portion is part of a sub-portion of the taxonomy data structure that is registered by the source with the NLC disambiguation engine as being able to be used by the NLC disambiguation engine to disambiguate ambiguous content, and wherein other portions of the taxonomy data structure are not able to be used by the NLC disambiguation engine to disambiguate ambiguous content.

18. The computer program product of claim 11, wherein the private content information is not exposed to users or resources that are not associated with the source or authorized access by the source when performing the method.

19. The computer program product of claim 11, wherein the portion of NLC comprises a portion of natural language content of a corpus of natural language content ingested into a cognitive system, and wherein the cognitive operation is one of a cognitive search operation for searching for matching natural language content to a search request submitted to the cognitive system or a cognitive question answering operation for generating a natural language answer to a input natural language question.

20. The computer program product of claim 11, wherein the portion of NLC comprises a message posted to a collaborative website by a user that is the source, and wherein the private content information comprises a set of messages posted to the collaborative website by users that are part of a private group of the collaborative website.

21. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to;

identify, in a corpus of natural language content, a portion of natural language content (NLC) that is determined to be ambiguous with regard to a context of the portion of NLC, thereby identifying an ambiguous content portion;

compare the ambiguous content portion to private content information associated with a source of the ambiguous content portion, wherein the private content information is content information accessible to users and resources associated with the source and is not accessible to users or resources that are not associated with the source;

identify a domain of the ambiguous content portion based on a domain of a matching portion of the private content information; and

perform a clarifying operation that clarifies the ambiguous content portion based on the identified domain of the ambiguous content portion to thereby generate a clarified content portion for processing by a cognitive operation of a cognitive system.