Pattern Identification and Correction of Document Misinterpretations in a Natural Language Processing System

• US 20160147734A1
• Filed: 11/21/2014
• Published: 05/26/2016
• Est. Priority Date: 11/21/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Allen, Corville O., Dettman, Elizabeth T., Freed, Andrew R., Payne, Michael T., Schroeder, Michael W.
• Granted Patent: US 9,678,947 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

An approach is provided in which a knowledge manager analyzes multiple document phrases using a natural language processing model and generates multiple interpretations based upon the analysis. The knowledge manager identifies misinterpretation patterns by comparing the multiple interpretations with multiple corrections that include corrections to the multiple interpretations. In turn, the knowledge manager generates interpretation rules based upon the identified patterns and applies the interpretation rules to the natural language processing model.

Claims

1. (canceled)

2. (canceled)

3. (canceled)

4. (canceled)

5. (canceled)

6. (canceled)

7. (canceled)

8. An information handling system comprising:

one or more processors;

a memory coupled to at least one of the processors; and

a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions of;

analyzing a plurality of document phrases using a natural language processing model, wherein the analyzing results in a plurality of interpretations;

generating one or more interpretation rules based upon one or more patterns corresponding to the plurality of interpretations, wherein the one or more patterns are identified by comparing the plurality of interpretations with a plurality of corrections that correct the plurality of interpretations; and

applying the one or more interpretation rules to the natural language processing model.

9. The information handling system of claim 8 wherein each of the plurality of document phrases includes a same first set of words, and wherein each of the plurality of interpretations is equivalent.

10. The information handling system of claim 9 wherein the one or more processors perform additional actions comprising:

determining a correct interpretation of the first set of words in response to detecting that each of the plurality of interpretations are incorrect; and

including the first set of words and the correct interpretation in a first one of the one or more interpretation rules.

11. The information handling system of claim 10 wherein the one or more processors perform additional actions comprising:

identifying one or more synonym set of words corresponding to the first set of words; and

generating one or more synonym interpretation rules, wherein each of the one or more synonym interpretation rules includes at least one of the one or more synonym set of words and the correct interpretation.

12. The information handling system of claim 10 wherein the one or more processors perform additional actions comprising:

identifying one or more complex sentence patterns corresponding to the first interpretation rule based upon one or more complex sentence structures, wherein each of the one or more complex sentence patterns include one or more additional entities selected from the group consisting of an adjective and a preposition; and

generating one or more complex interpretation rules based upon the one or more complex sentence patterns, wherein each of the one or more complex interpretation rules includes the first set of words, the correct interpretation, and one or more of the additional entities.

13. The information handling system of claim 8 wherein the natural language processing model performs syntactic analysis and semantic analysis on each of the plurality of document phrases.

14. The information handling system of claim 8 wherein the one or more processors perform additional actions comprising:

evaluating a different document phrase using the natural language processing model based on the one or more interpretation rules, wherein the evaluating comprises;

generating a probabilistic score based upon a sentence similarity between the different document phrase and one of the one or more interpretation rules; and

utilizing the probabilistic score to rank a different interpretation of the different document phrase.

15. A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, causes the information handling system to perform actions comprising:

analyzing a plurality of document phrases using a natural language processing model, wherein the analyzing results in a plurality of interpretations;

generating one or more interpretation rules based upon one or more patterns corresponding to the plurality of interpretations, wherein the one or more patterns are identified by comparing the plurality of interpretations with a plurality of corrections that correct the plurality of interpretations; and

applying the one or more interpretation rules to the natural language processing model.

16. The computer program product of claim 15 wherein each of the plurality of document phrases includes a same first set of words, and wherein each of the plurality of interpretations is equivalent.

17. The computer program product of claim 16 wherein the information handling system performs additional actions comprising:

determining a correct interpretation of the first set of words in response to detecting that each of the plurality of interpretations are incorrect; and

including the first set of words and the correct interpretation in a first one of the one or more interpretation rules.

18. The computer program product of claim 17 wherein the information handling system performs additional actions comprising:

identifying one or more synonym set of words corresponding to the first set of words; and

generating one or more synonym interpretation rules, wherein each of the one or more synonym interpretation rules includes at least one of the one or more synonym set of words and the correct interpretation.

19. The computer program product of claim 17 wherein the information handling system performs additional actions comprising:

identifying one or more complex sentence patterns corresponding to the first interpretation rule based upon one or more complex sentence structures, wherein each of the one or more complex sentence patterns include one or more additional entities selected from the group consisting of an adjective and a preposition; and

generating one or more complex interpretation rules based upon the one or more complex sentence patterns, wherein each of the one or more complex interpretation rules includes the first set of words, the correct interpretation, and one or more of the additional entities.

20. The computer program product of claim 15 wherein the natural language processing model performs syntactic analysis and semantic analysis on each of the plurality of document phrases.