Jaguar and Jager: Automate Ontology Building

Jaguar™ takes input from your documents and recognizes important concepts and semantic relations between them that comprise a searchable ontology. The input can be reports, audits, web pages, emails, tweets, social media content, user manuals, etc. in various file formats. The resulting ontology is in a standard OWL format and can be browsed and edited in our Jager™ web application.

High level architecture

Jaguar can build domain ontology independently, starting with a handful of seed concepts. Additionally, it can incorporate elements from your existing OWL ontology, database schema, key word list or user defined taxonomy as the basis to filter new input for semantic relevance and construct hierarchical concepts and relationships discovered in the text. Optionally, a more detailed semantic representation can be derived in addition to ontology. This additional output defines 26 different types of semantic relationships to enable your knowledge to be structured into a usable Knowledge Base.

Jager makes it easy to review, browse and edit the output from Jaguar for added precision. In Jager, you can view the source phrases and sentences that were pulled from your documents to extract the semantic relationships.

Jaguar and Jager can be purchased independently or together with K-Extractor for complete knowledge management.

In the figure below an illicit drugs ontology has a branch for criminal organizations under which Heriberto Lazcano is classified as a leader and member of Los Zetas. His association with Miguel Trevino Morales, and his aliases are listed as part of his semantic context, each relation having been discovered from text.

Jager's interactive ontology interface