In software, semantic technology encodes meanings separately from data and content files, and separately from application code. This enables machines as well as people to understand, share and reason with them at execution time.
When it comes to humans, semantic memory is one of the two types of declarative or explicit memory. Semantic memory refers to general world knowledge that we have accumulated throughout our lives. Everything from dates, addresses, history and common sense things like how to boil an egg or drive a car. This general knowledge is intertwined in experience and dependent on culture. What someone learns in Pittsburgh, Pennsylvania will likely be very different from what someone learns in Paris, France.
Semantic memory is distinct from episodic memory, which is our memory of experiences and specific events that occur during our lives, from which we can recreate at any given point. This is the “walk down memory lane” kind of memory.
For instance, semantic memory might contain information about what a guitar is, whereas episodic memory might contain a specific memory of listening to a guitar being played around a campfire.
So, back to semantic technology. With traditional information technology ,meanings and relationships must be predefined and hard wired into data formats and the application program code at design time. This means that when something changes, previously unexchanged information needs to be exchanged, or two programs need to interoperate in a new way, the humans must get involved. This is back to basics, i.e. if a=1, etc.
Semantic technologies are meaning-centered. They have the capability of recognition of topics and concepts, information and meaning extraction, and categorization – automatically. Given a question, semantic technologies can directly search topics, concepts, associations that span a vast number of sources.
Semantic methodologies also support a variety of other applications in big data environments, like artificial intelligence (AI). Because semantic technology is able to encode meaning into content, a computer system can have a human-like understanding and reasoning. Basically, semantic technology is able to create links between data points within documents and other forms of data containers that helps these intelligent agents in providing precise answers.
Semantic technologies have been around for more than 40 years. The application of these technologies make possible the natural language processing (NLP) capabilities of IBM Watson and the ongoing refinement of Google search results, to name a few.
The future holds more potential and possibilities as semantic technology continues to evolve.
Melody K. Smith
Sponsored by Access Innovations, the world leader in thesaurus, ontology, and taxonomy creation and metadata application.
