Semantic Search with Hakia

A fairly new approach to overcome the problems with the set up of the semantic web is the development of semantic search engines. Instead of relying on the (mostly not existent) semantic annotations of web pages, these engines are powered by a semantic model of the world and should be able to “understand” the content of arbitrary web pages. This approach differs from search engines for the semantic web, like Swoogle which only searches and analyses pages with semantic annotations. One such a semantic search engine is Hakia.

ReadWriteWeb published an Article of the Hakia CEO Dr. Riza C. Berkan about the semantic search approach and its challenges:
Semantic Search: An Antidote for Poor Relevancy. Semantic search is seen as one of the next-generation search methods that may challenge Google. Dr. Berkan mentioned on this:

Will semantic search take over today’s search engines?

A. In the long run, they most likely will. Again, this depends on how well they are done. Once the long-tail searches start to show the difference, then it will probably have a domino effect. If people are satisfied in the complex query domain, they are more likely to switch for simple queries as well. Let’s remember that there is no cost to switch.

Another interview with Dr. Berkan can be found at profy.com: Interview - Dr. Berkan, hakia Mastermind.

People have real problems that search engines cannot address. They have health, money, relational and other personal issues that search does not address. Eventually, hakia will be able to address these real world issues with tangible, valuable and actionable results. (Dr. Berkan)

So let’s give it a try. The power of semantic search lies in the understanding of the searcher’s needs. So generally, these engines provide better results for longer search queries and queries that are formulated as questions. I played around with the engine and here are some of my favorite results:

On my first question, “What is the capital of Germany?, Hakia returned a Gallery about Germany, filled with a lot of information, like the population, the flag and so on. Indeed, the correct answer (Berlin) is also found. The basic information are taken from the CIA World Factbook.

I extended this question to “Is Berlin or Bonn the capital of Germany?” and got the following impressing answer:

Would you consider this answer? Berlin was capital of East Germany while Bonn was capital of West Germany but with the unification of two countries in 1990, Berlin became the capital. See this page. …See the hakia gallery for Germany

With the next Question, “What is the meaning of life?”, Hakia caught me. Probably I was not the first one to try this question, so they presented me the Hakia Gallery for the Meaning of Life.

But then again, Hakia surprised me with a nice answer to another fundamental question: “Does God exist?”

Check this out: Like virtually all of our other knowledge, I think we can show that it is highly probable that God exists. See this page.

On this track, I (of course) had a last one: “What is the answer to life, the universe and everything?”

This may lead to a good answer: Released on September 11, 2002, the Answer to Life, the Universe, and Everything set out to find happiness. See this page.

Damn, they missed it… But fortunately, the first two hits came up with the only right answer:

The Answer to Life, Universe and Everything Open this page in a new window
actually happened: After we figured out that Answer to Life, Universe and everything is 42
http://geekswithblogs.net/codepersona/archive/2006/07/08/84496.aspx

The answer to life the universe and everything Open this page in a new window
According to the Google calculator, the answer to life the universe and everything = 42. I’m not quite sure how
http://ben.milleare.com/2003/09/14/the-answer-to-life-the-universe-a…

These examples can give you an idea of the semantic search approach. I tested Hakia with the common one or two word queries we all mostly use with Google, too. The results were not bad but yet not substantially better than the Google results. But nevertheless, Hakia can at least be considered as an additional search engine if your next Google search reveals a lot of irrelevant results. If you get used to formulate your queries as questions with as much as possible additional information about the context, then you probably can choose a semantic search engine like Hakia as your primary one. Give it a try!

Technorati , , , , ,

2 Responses to “Semantic Search with Hakia”

  1. K.A.I.E.C. » Blog Archive » Semantic Search with Lexxe Says:

    […] K.A.I.E.C. Kai’s Automatic Indexing Evaluation Center « Semantic Search with Hakia […]

  2. K.A.I.E.C. » Blog Archive » Semantic Search with AskWiki Says:

    […] in my posts about semantic search with Hakia and Lexxe, Tim Finin posted a set of questions posed to AskWiki, a semantic search engine that uses […]

Leave a Reply