Method and apparatus to extrapolate sarcasm and irony using multi-dimensional machine learning based linguistic analysis
View Patent ↗A system, method, and computer-readable medium for performing ambiguous utterances identification operations by extrapolating statements of the utterance using machine learning based linguistic analysis. More specifically, in certain embodiments, the ambiguous utterances identification operations are performed by generating an ambiguous utterance repository that is indexed by and contains individuals, regions, tweets, blogs, and latest trends. This ambiguous utterance repository is then linked to a lexicon engine that stores linguistic semantics for particular demographics. The ambiguous utterances identification operations also can capture the latest trends in ambiguous utterances occurring happening in certain demographics.
1. A computer-implementable method for performing an ambiguous utterance identification operation, comprising:
receiving a plurality of ambiguous utterances, each of the plurality of ambiguous utterances comprising an utterance that has an uncertain meaning in a context the utterance appears;
indexing the plurality of ambiguous utterances to provide a plurality of indexed ambiguous utterances;
storing the plurality of indexed ambiguous utterances in an ambiguous utterance repository;
identifying a statement as an ambiguous utterance using machine learning based linguistic analysis and the ambiguous utterance repository;
storing linguistic semantics for particular demographics within a lexicon engine; and,
linking the ambiguous utterance repository to the lexicon engine.
2. The method of claim 1 , wherein:
the plurality of ambiguous utterances are indexed by individuals, regions, tweets, blogs, and trends.
3. The method of claim 1 , further comprising:
capturing trends in ambiguous utterances occurring in certain demographics; and,
storing information relating to the trends in ambiguous utterances occurring in certain demographics within the ambiguous utterance repository.
4. The method of claim 3 , further comprising:
ranking the trends in ambiguous utterances occurring in certain demographics based on the occurrence.
5. The method of claim 4 , further comprising:
storing the ranking in a heuristic engine;
extracting ambiguous utterances from the trends using templates.
6. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
receiving a plurality of ambiguous utterances, each of the plurality of ambiguous utterances comprising an utterance that has an uncertain meaning in a context the utterance appears;
indexing the plurality of ambiguous utterances to provide a plurality of indexed ambiguous utterances;
storing the plurality of indexed ambiguous utterances in an ambiguous utterance repository;
identifying a statement as an ambiguous utterance using machine learning based linguistic analysis and the ambiguous utterance repository;
storing linguistic semantics for particular demographics within a lexicon engine; and,
linking the ambiguous utterance repository to the lexicon engine.
7. The system of claim 6 , wherein
the plurality of ambiguous utterances are indexed by individuals, regions, tweets, blogs, and trends.
8. The system of claim 7 , wherein the instructions executable by the processor are further configured for:
storing linguistic semantics for particular demographics within a lexicon engine; and,
linking the ambiguous utterance repository to the lexicon engine.
9. The system of claim 6 , wherein the instructions executable by the processor are further configured for:
ranking the trends in ambiguous utterances occurring in certain demographics based on the occurrence.
10. The system of claim 9 , wherein the instructions executable by the processor are further configured for:
storing the ranking in a heuristic engine;
extracting ambiguous utterances from the trends using templates.
11. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
receiving a plurality of ambiguous utterances, each of the plurality of ambiguous utterances comprising an utterance that has an uncertain meaning in a context the utterance appears;
indexing the plurality of ambiguous utterances to provide a plurality of indexed ambiguous utterances;
storing the plurality of indexed ambiguous utterances in an ambiguous utterance repository; and,
identifying a statement as an ambiguous utterance using machine learning based linguistic analysis and the ambiguous utterance repository;
storing linguistic semantics for particular demographics within a lexicon engine; and,
linking the ambiguous utterance repository to the lexicon engine.
12. The non-transitory, computer-readable storage medium of claim 11 , wherein
the plurality of ambiguous utterances are indexed by individuals, regions, tweets, blogs, and trends.
13. The non-transitory, computer-readable storage medium of claim 12 , wherein the computer executable instructions are further configured for:
storing linguistic semantics for particular demographics within a lexicon engine; and,
linking the ambiguous utterance repository to the lexicon engine.
14. The non-transitory, computer-readable storage medium of claim 11 , wherein the computer executable instructions are further configured for:
ranking the trends in ambiguous utterances occurring in certain demographics based on the occurrence.
15. The non-transitory, computer-readable storage medium of claim 14 , wherein the computer executable instructions are further configured for:
storing the ranking in a heuristic engine;
extracting ambiguous utterances from the trends using templates.