Input/Output
The flexible nature of the Janya’s text analytic system allows for any number of source types including, news, blogs, translated text (FBIS) e-mail, technical documents, transcribed audio and classified (HUMINT) documents. See our information extraction pre-processing technology.
Janya’s tokenlist results structure contains all the output of a single document including any location or time normalization and relationships between entities. This XML structure may be converted to meet the specifications of a user or 3rd or a proprietary database such as TMODS.
The output of an individual documents may then be further analyzed using some of the same technology as the engine itself to relate with other documents creating richer, entity profiles and event scenarios. See Corpus Level Fusion.
