In a nutshell textUrgy takes unstructured text as an input, performs a semantic analysis using our patented technology, and returns structured information. By unstructured text we mean text (in a document of some sort) that has not been tagged or structured in any way. After texturgy has done its magic we have extracted useful information from the text such as entities, themes, tags and even relationships between entities/entities, entities/theme or theme/theme.

The textUrgy classification library plays a key role during the extraction of semantic structure. The library is being continuously developed and consists of more than 400 000 words. In addition textUrgy is able to import other classification libraries / taxonomies to meet industry specific needs.

The architecture supports Linked Open Data (LOD), both in terms of getting information from other places in the LOD cloud as well as making information available to the LOD cloud.