Analogy outcome determination

• US 10,331,718 B2
• Filed: 10/06/2016
• Issued: 06/25/2019
• Est. Priority Date: 10/06/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Allen, Corville O., Freed, Andrew R.
• Primary Examiner(s): Spieler, William
• Application Number:
  US15/287,123
• Publication Number:
  US 20180101602A1
• Time in Patent Office: 992 Days
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. A phrase is compared to an analogy classifier database in order to identify a match between the analogical pattern and an analogy entry. If a match is identified, generating an idiomatic structure from the analogical pattern. An analysis is then applied whereby the analysis includes building a set of outcomes of the generated idiomatic structure based on semantic analysis into corresponding metadata for the idiomatic structure. An ontological database is searched for evidence of a pattern associated with the set of outcomes and each entry in the outcome set is scored according to a weighted calculation from the ontological database based on congruence with the pattern. An entry from the outcome set is selected based on the scoring and is represented as a meaning of the analogical pattern.

Claims

1. A computer system comprising:

a processing unit operatively coupled to memory;

an artificial intelligence platform, in communication with the processing unit;

a tool in communication with the processing unit to decipher a phrase upon activation by the artificial intelligence platform, including the tool to;

compare the phrase to an analogy classifier database to identify a match between the phrase and an analogy entry;

upon identifying a match, generate an idiomatic structure from the phrase;

apply an analysis, including building a set of outcomes of the generated idiomatic structure based on semantic analysis into corresponding metadata for the idiomatic structure;

search an ontological database for evidence of a pattern associated with the set of outcomes;

score each entry in the outcome set according to a weighted calculation from the ontological database based on congruence with the pattern; and

select an entry from the outcome set based on the scoring, and representing the selected entry as a meaning of the phrase.

2. The computer system of claim 1, further comprising the tool to populate a corpus with the represented meaning of the phrase, including submitting the selected entry into the corpus.

3. The computer system of claim 1, further comprising the tool to expand the metadata, including generating a list of sub-types from ontology terms in the phrase.

4. The computer system of claim 1, further comprising the tool to identify an adjective associated with a second verb phrase, and apply the adjective to filter the list of definitions.

5. The computer system of claim 4, further comprising the tool to adjust the outcome, the adjustment including searching a corpus for evidence of sub-types from ontologies of a first verb phrase.

6. The computer system of claim 4, further comprising the tool to:

for one or more of the sub-types in the list, perform an expansion selected from the group consisting of a hyponym expansion and a hypernym expansion;

wherein the hyponym expansion includes searching the corpus of evidence of the hyponym expansion and applying a score to each hyponym according to its incidence in the corpus; and

wherein the hypernym expansion includes searching the corpus of evidence of the hypernym expansion and applying a score to each hypernym according to its incidence in the corpus.

7. A computer program product for deciphering a phrase, the computer program product comprising a computer readable storage device having program code embodied therewith, the program code executable by a processing unit to:

compare a phrase to an analogy classifier database to identify a match between the phrase and an analogy entry;

upon identifying a match, generate an idiomatic structure from the phrase;

apply an analysis, including building a set of outcomes of the generated idiomatic structure based on semantic analysis into corresponding metadata for the idiomatic structure;

search an ontological database for evidence of a pattern associated with the set of outcomes;

score each entry in the outcome set according to a weighted calculation from the ontological database based on congruence with the pattern; and

select an entry from the outcome set based on the scoring, and representing the selected entry as a meaning of the phrase.

8. The computer program product of claim 7, further comprising the processing unit to populate a corpus with the represented meaning of the phrase, including submitting the selected entry into the corpus.

9. The computer program product of claim 7, further comprising the processing unit to expand the metadata, including generating a list of sub-types from ontology terms in the phrase.

10. The computer program product of claim 7, wherein a list of definitions for the list from ontology terms in the phrase include a definition, a subject term, a first verb phrase, a second verb phrase, a comparator, and an object.

11. The computer program product of claim 10, further comprising the processing unit to identify an adjective associated with the second verb phrase, and apply the adjective to filter the list of definitions.

12. The computer program product of claim 11, further comprising the processing unit to adjust the outcome, the adjustment including searching a corpus for evidence of sub-types from ontologies of the first verb phrase.

13. The computer program product of claim 11, further comprising the processing unit to:

for one or more of the list of sub-types from ontology terms in the list of definitions, perform an expansion selected from the group consisting of a hyponym expansion and a hypernym expansion;

wherein the hyponym expansion includes searching a corpus of evidence of the hyponym expansion and applying a score to each hyponym according to its incidence in the corpus; and

wherein the hypernym expansion includes searching the corpus of evidence of the hypernym expansion and applying a score to each hypernym according to its incidence in the corpus.

14. A method, in an information handling system comprising a processor and memory, to resolve a definition of an analogical pattern, the method comprising:

comparing a phrase to an analogy classifier database to identify a match between the phrase and an analogy entry;

upon identifying a match, generating an idiomatic structure from the phrase;

applying an analysis, including building a set of outcomes of the generated idiomatic structure based on semantic analysis into corresponding metadata for the idiomatic structure;

searching an ontological database for evidence of a pattern associated with the set of outcomes;

scoring each entry in the outcome set according to a weighted calculation from the ontological database based on congruence with the pattern; and

selecting an entry from the outcome set based on the scoring, and representing the selected entry as a meaning of the phrase.

15. The method of claim 14, further comprising populating a corpus with the represented meaning of the phrase, including submitting the selected entry into the corpus.

16. The method of claim 14, further comprising expanding the metadata, including generating a list of sub-types from ontology terms in the phrase.

17. The method of claim 16, wherein a list of definitions for the list from ontology terms in the phrase include a definition, a subject term, a first verb phrase, a second verb phrase, a comparator, and an object.

18. The method of claim 17, further comprising identifying an adjective associated with the second verb phrase, and applying the adjective to filter the list of definitions.

19. The method of claim 18, further comprising adjusting the outcome, the adjustment including searching a corpus for evidence of sub-types from ontologies of the first verb phrase.

20. The method of claim 18, further comprising:

for one or more of the list of sub-types from ontology terms in the list of definitions, performing an expansion selected from the group consisting of a hyponym expansion and a hypernym expansion;

wherein the hyponym expansion includes searching a corpus of evidence of the hyponym expansion and applying a score to each hyponym according to its incidence in the corpus; and

wherein the hypernym expansion includes searching the corpus of evidence of the hypernym expansion and applying a score to each hypernym according to its incidence in the corpus.