Current search technologies are based on statistical algorithms that match the words you enter in the search box with words that exist at a website. Search engines attempt exact matches, and present the results on the search engine results pages (SERPs) ranked according to how closely the website’s words match the search words you entered.
The next generation of search engines will use techniques from linguistic science to determine the semantic relationships between words and the contexts in which they occur.
Wikipedia defines the Semantic Web as
The semantic web is an evolving extension of the World Wide Web in which web content can be expressed not only in natural language, but also in a form that can be understood, interpreted and used by software agents, thus permitting them to find, share and integrate information more easily.
For the purposes of this post, the “software agents” would be the search engine programs that process your search. Wikipedia goes on to explain:
Humans are capable of using the Web to carry out tasks such as finding the Finnish word for “car”, to reserve a library book, or to search for the cheapest DVD and buy it. However, a computer cannot accomplish the same tasks without human direction because web pages are designed to be read by people, not machines. The semantic web is a vision of information that is understandable by computers, so that they can perform more of the tedium involved in finding, sharing and combining information on the web.
For example, a computer might be instructed to list the prices of flat screen HDTVs larger than 40 inches with 1080p resolution at shops in the nearest town that are open until 8pm on Tuesday evenings. To do this today requires search engines that are individually tailored to every website being searched. The semantic web provides a common standard (RDF) for websites to publish the relevant information in a more readily machine-processable and integratable form.
The difference between the two search techniques is the results they produce. The search engines using semantic search will attempt to interpret your intention and serve up information that is “related” to your search terms while the engines using the “exact match” technique will continue to serve up information that matches words, but, that may not be relevant to your intention, requiring your discretionary powers (human intervention) to determine the most relevant information.