Carsten Kraus is chief executive of Europe’s leading online search specialist and semantic search pioneer, FACT-Finder
With the announcement that Google will be using semantic search technology as the backbone for its latest “drastic” makeover – which will see the search engine giant endeavour to actually help users answer questions rather than simply hunt down words – it looks as though the much hyped “next big step” in search engine functionality is finally ready to hit the mainstream.
Until relatively recently, this technology has been out of reach of the average internet searcher, but within the next few months, if we are to believe the press, the bulk of search activity going through Google will be based on semantics.
Google searches will no longer simply throw up a list of blue links – instead, the top of the results page will be dotted with information that ‘answers questions’ posed in searches.
One of the cornerstones to semantic search is having access to vast amounts of data to be able to feed users’ information about what they are searching for. Google has quietly amassed information on 200 million ‘entities’ – from people and places to products – and this would certainly bear out the search giant’s claims.
As yet, no one has seen Google’s semantic search technology. While the search giant may be making the most high-profile splash in the semantics arena, the technology has actually been in operation on a number of big websites for some time already.
In the travel sector, for example, Thomas Cook’s German subsidiary Neckermann Urlaubswelt started using the technology earlier this year, joining another German travel site weg.de, which has been using it on its homepage since January after a two-month test.
With the speed at which the vast number of queries Google receives need to be processed, the probability is that it will not be using any kind of semantic search function that is currently available – these take longer to process requests than traditional keyword systems. It is likely instead that Google will be using a mix of semantic and keyword search technology.
True semantic search uses an inference engine, which means that instead of simply trying to match the words that have been typed in, it analyses its own knowledge repository (“Ontology”), to try and understand the words and draw its own conclusions. For instance, if someone were to be searching for ‘beach holiday around Christmas’ the inference here would be that the destination they are looking for should be warm.
However, the level of functionality offered by semantics depends on how advanced this engine is, and on top of this there are also limitations to those engines using standard inference semantic search systems with respect to the intelligence of the search. For example, if you were looking to take a break in Scotland over New Year, and wanted to be able to go for long walks on a nearby beach you might search: ‘Scotland New Year with beach’.
While this is a valid request, if you asked a normal inference engine it would reject it, because it would associate the term ‘beach’ with someone looking for a warm holiday – and it is never going to be ‘warm’ in Scotland over New Year.
We have solved this problem by creating a “probabilistic” inference engine that scores rather than judges information, combining semantics with the fuzzy logic approach – which we’ve been using since the mid-1990s. There may be other ways to do this, but the problem of real-life ambiguity has to be solved to make semantic search more than a cute toy, and we have found this to be an effective way of rising to this challenge.
The ability to type a query in your own words and have the search engine understand the inferences of the language is a huge step in search technology. This has major implications for ecommerce, and research has shown that on travel websites, as soon as consumers understand how the technology works and that they can really type in what they want, it takes them one third of the time to find the right product compared to conventional search.
However, to take full advantage of semantic search our searching habits will have to change; moving from asking primitive queries, as we have all become conditioned, to entering free-form queries in our own words. This is where the power of semantic search lies and the technology for intelligent searching is now well within our grasp – if Google really is leading the field in the way it claims then this is a change we will all be making very soon.