Text classification using models with complementary granularity and accuracy
AssigneeInternational Business Machines Corporation
InventorsJian Ni, Radu Florian, Salim Roukos, Vittorio Castelli
Life of this patent
Estimating the term…
Abstract
A processor may receive a text segment. The processor may analyze the text segment at a plurality of granularity levels wherein each of the plurality of granularity levels has a comparative selection value for identifying one or more objects of interest within the text segment. The processor may select an optimized granularity level with an optimum comparative selection value. The processor may identify the one or more objects of interest within the text segment. The processor may display the one or more objects of interest to a user.
Claims20
A method for text classification at multiple levels of granularity with different accuracies, said method comprising:
- receiving a text segment via a processor;
- analyzing said text segment on a plurality of granularity levels wherein each of said plurality of granularity levels has a comparative selection value for identifying one or more objects of interest within said text segment;
- selecting an optimized granularity level wherein said optimized granularity level has an optimum comparative selection value;
- identifying said one or more objects of interest within said text segment;
- and
- displaying said one or more objects of interest to a user.
A system for text classification at multiple levels of granularity with different accuracies, said system comprising:
- a memory;
- and
- a processor in communication with said memory wherein said processor is configured to perform operations comprising:
- receiving a text segment;
- analyzing said text segment on a plurality of granularity levels wherein each of said plurality of granularity levels has a comparative selection value for identifying one or more objects of interest within said text segment;
- selecting an optimized granularity level wherein said optimized granularity level has an optimum comparative selection value;
- identifying one or more objects of interest within said text segment;
- and
- displaying said one or more objects of interest to a user.
A computer program product for data classification via text analysis, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, said program instructions executable by a processor to cause said processor to perform a function, said function comprising:
- receiving a text segment;
- analyzing said text segment on a plurality of granularity levels wherein each of said plurality of granularity levels has a comparative selection value for identifying one or more objects of interest within said text segment;
- selecting an optimized granularity level wherein said optimized granularity level has an optimum comparative selection value;
- identifying said one or more objects of interest within said text segment;
- and
- displaying said one or more objects of interest to a user.
Dependencies are inferred from the claim text.