History and Context


As early as the 1980s significant research appeared in information science literature about the development of expert systems for improving search results.Hundreds of universities, start-up companies, and major corporations have published research and filed patents on various algorithmic techniques for machine-aided searching over three decades (and earlier when much of this work was classified as artificial intelligence). By the late 1990s and early 2000s, these technologies began to be described as semantic search components.In 2001 Tim Berners-Lee published an article in Scientific American proposing a semantic web evolving out of the expanding worldwide web.

Quite simply, the vision of semantic search is the availability of software algorithms that would improve retrieval for the average person by interpreting their native inquiry and returning semantically relevant results. The idea is that something as mundane as typing, “where can I find a gas station in Bolton, Mass?” could be answered as accurately by a search engine as by a human being.On the internet, this would be a “semantic web” query.

As web search engines continue to improve, good results to such a query have become a reality. This type of Q & A often makes use of a semantic technology called “natural language processing,” one of many related technologies that comprise the semantic software technology landscape.

However, in the enterprise, expectations for relevant search results are much higher than for finding content already optimized for e-commerce on the web. Each business unit in an organization has specialized requirements for finding information needed to do its work more efficiently. This is where other types of semantic processing can give organizations a competitive edge by getting workers to answers more quickly, with more conceptual relevance, and even with pinpoint accuracy. The idea is to get only the right information (only relevant) and all the right information (everything that is relevant).

In the enterprise, semantic content technologies and “intelligent indexing” improve retrieval in many vertical domains and for numerous functions. This covers a spectrum from finding a single critical engineering drawing for completing manufacturing plans, to discovering an e-mail thread that might absolve a client in litigation, retrieving all available research in the past year on a particular gene biomarker, or collecting all invoices submitted to a delinquent customer.