Ok, what the heck is compound term processing – and why do I care?
The generation of semantic metadata enables the agency to extract compound terms, acronyms, and keywords from a document or corpus of documents that are highly correlated to a particular concept or metatag. By identifying the most significant patterns in any text, these compound terms are then used to generate metadata based on an understanding of conceptual meaning. This eliminates the requirement for an individual to read a document and subjectively apply metadata to that document. This ability to identify ‘concepts in context’ through our unique compound term processing technology eliminates inconsistent or non-existent tagging processes and overcomes different publishing conventions that may exist within the agency.
The below graphic illustrates the results using compound term processing. In this example the search term ‘triple heart bypass’ would typically return results containing each of the words in the result set. Using compound term processing the technology understands that the query (i.e. triple heart bypass) is a concept and will retrieve documents based on the compound terms.
The metadata generation occurs in real-time as content is either created or ingested, and can be immediately available to a wide variety of applications. Manual metadata generation among stove-piped systems add unacceptable cost and time that compromises effective operations. With the ability to overcome incompatible semantics and meanings provides a method of bridging vocabularies across global boundaries.