9 Semantic Search Engines That Will Change the World of Search

SMS Text

The ideal search engine would be able to match the search queries to the exact context and return results within that context. While Google, Yahoo and Live continue to hold sway in search, here are the engines that take a semantics (meaning) based approach, the end result being more relevant search results which are based on the semantics and meaning of the query, and not dependent upon preset keyword groupings or inbound link measurement algorithms, which make the more traditional search engines easier to game, thus including more spam oriented results.

Here is a wrap up of some of the top semantic search engines which we’ve covered previously, and some updates on their research.

1. Hakia

The brainchild of Dr. Riza C. Berkan, tries to anticipate the questions that could be asked relating to a document and uses them as the gateways to the content.


The search queries are mapped to the results and ranked using an algorithm that scores them on sentence analysis and how closely they match the concept related to the query.

Hakia semantic search is essentially built around three evolving technologies:

  1. OntoSem (sense repository)
  2. QDEX (Query indexing technique)
  3. SemanticRank algorithm
  • OntoSem is Hakia’s repository of concept relations, in other words, a linguistic database where words are categorized into the various “senses” they convey.
  • QDEX is Hakia’s replacement for the inverted index that most engines use to save web content. QDEX extracts all possible queries relating to the content (leveraging the OntoSem for meaning) and these become the gateways to the original document. This process greatly reduces the data set that the indexer has to deal with while querying data on-the-fly. An advantage when you considering the wide swath of data the engine would have to search if it were an inverted index.
  • Finally, the SemanticRank algorithm independently ranks content on the basis of more sentence analysis. Credibility and age of the content is also used to determine relevancy.

Hakia performs pure analysis of content irrespective of links or clickthroughs among the documents (they are opposed to statistical models for determining relevance).

The engine has also started using the Yahoo BOSS service and also presents results in a “gallery” with categories for different content matching the query. Users can also request to try out the the incremental changes that are being tried at Hakia’s Lab.

2. Kosmix


The search company has takes its categorization concept further by providing users with a dashboard of content, aptly called – ” Your guide to the Web”. The company’s focus on informational search makes it suitable for topics when you want information on it rather than look for a particular answer or URL. For example, the search for Credit Default Swap provided a great mix of links, videos and tweets to get me started. Kosmix received $20 million of funding from Time Warner in late 2008. Its content aggregating technology will become more important as content on the web grows.

3. Exalead


The image search engine was unique for its host of options to narrow down search based on image size, color and content. Many of these features have since appeared across other image search engines. Exalead is a must try for image search. The company has been focusing on the enterprise search market, essentially attempting to solve the problem of search for content where link analysis is of little help.

4. SenseBot

The technology powering this engine creates a summary of the top results that are returned for a user query, often negating the need to drill down into the URLs to get the information that one is seeking. Semantic Engines LLC, the company behind the engine provides a variety of products around this technology.


There is Link Sensor, a tool  that can be used on major blogging platforms (WordPress, Blogger, etc.)for automatically picking up key concepts from the post and linking them to related articles from the same blog or publisher. It is possible to point to other venues as well, e.g. to another blog from the same publisher – perhaps with a higher CPM. The tool increases user engagement. The company has also started providing APIs for returning summaries of results for a query from a set of URLs that are also passed in as parameters to the APIs. This is one interesting approach that helps save time when an exact answer is what one is looking for.

5. Cognition Search

cognition search

The Cognition Search NLP Product is a solution companies can use to extract relevant results from their content. The application of this technology could range from better search across the enterprise to fetching more relevant ads. The company provides APIs for access to these technologies. I could not locate the free search, but definitely with the showdown featured on GigaOM, the product has its utility. And it also provides a definite business model.

6. Lexxe

The Questions and answer search engine uses linguistics to answer the questions that are posed as queries.


Its a good site to try out egosurfing (how popular you are on the web). The engine also provides keywords that represent categories for the results, clicking which takes you to more relevant topics for the query.

7. Swoogle


Swoogle is strictly for the semantic web. The engine indexes documents developed on the concepts and standards for semantics (such as the RDF Format). : Swoogle

8. Factbites


The aim of the engine is to return meaningful sentences for the search query. Its a technique that lies midway between a site summary and summary of all results. For example, the search for  gives enough to answer what is the Semantic Web.

9. Powerset

After being acquired by Microsoft, the changes to live search were noticeable in the related searches and content returned from Wikipedia. Of course most of the changes would be transparent but definitely in the longer run we can expect more additions to live search.

Overall, any search engine has certain major challenges to make a serious dent in the search space. These include faster return of results, more accurate results for less keywords (three to four words maximum) and more awareness on the side of users.


Most of the problems that face upcoming search engines are not even related to relevancy of results. The appeal of semantic search engines is that the content of a page alone decides its utility. This means lesser spam and of course more relevant ads. It would be harder to game a semantic web engine. Whether a search engine can meet all these criteria continues to remain a question.

Get the latest news from Search Engine Journal!
We value your privacy! See our policy here.
  • Hey Arun, I don’t normally comment on blogs but your post was a real call to action. Thank you for a great read, I will be sure to bookmark your site and check in now and again.

  • The problem here is whether or not anyone will actually use any of these engines. You can have all the fancy queries and algorithms that you want but if no one knows about them, do “they” even matter? The principal behind it all is great, I just don’t see people giving up on using Google and any of these being a real game changer anytime soon.

    Good post either way.

  • Arun

    @ Sazha

    Thank you.

    @ Devilman676

    Indeed, the problem for any of these engines goes beyond just getting better results. They have to scale to index the whole web while still returning results in fraction of a second. And they have to get popular among netizens used to googling on, well, google, yahoo and Live. But I think the greater possibility is of taking search to a higher level such that it can be part of online activities than just another web application. This would require algorithms that can make better sense of data and this is where I personally think that Semantic engines can contribute a lot. Thank you for sharing your views.

  • I think these engine will change search as you say, by being acquired and integrated into the offering of a major player.

    Also, you forgot one of the strongest entries: Evri. Evri.com has indexed massive amounts of content already and shows great potential as a unique offering.

    I have no connection to the company. Just wanted to point that out.

  • Great post Arun! Really interesting stuff.
    I agree that the major challenge is scaling up and bringing the users.

    If you’re interested in another view of the semantic web , check out http://www.urlclassifier.com semantic web-service for online extracting topics from URLs (some great search possibilities there also). This is by ContextIn Semantic Advertising algorithms

  • Arun

    @ ian
    @ Ben Stein

    Thanks for the heads up. Will surely explore those engines.

  • Thanks @ian!
    Arun, you should check out what we are doing. We don’t really push our “search engine” — but our technology is under all we do. Our Search interface is here: http://www.evri.com/mainline-ui/jsp/search.jsf

    and here is a search that you really can’t do on any of the above (or Goog of course, but this isn’t what they are even trying to do…): http://tinyurl.com/cn77g4

    The query (in our search language) is: “[company] > buy > [company] ^ [money]”

    Which means “Show me companies who have bought (or talked about buying) other companies, where the prepositional complement is a monetary amount”

    email with any questions.

  • This is superb and never have I come upon these ones. Relevancy is key, especially when designing your site for the engine, these sites will provide even more insight!

  • prowse

    devilma676 makes me laugh: this article and ones like it is precisely how one gets the word out on these fledgling and not-so-fledgling search engines!

  • Arun, also check out our new search engine Duck Duck Go: http://duckduckgo.com/

    We have a number of semantic properties including ambiguous keyword detection, e.g. http://duckduckgo.com/?q=apple

    I’d love your feedback,

    Gabriel Weinberg, Founder & CEO

  • sexy lingerie shows up. what the?

  • @kevin, the search engine is at http://swoogle.umbc.edu/

  • @kevin – nice try.

  • Great post on Semantic engines. I also believe it holds the answer to one day being able to ANSWER our questions instead of return results based on keywords.

    I have covered Hakia specifically and what its good for here for those of you interested!


  • This is superb and never have I come upon these ones. Relevancy is key, especially when designing your site for the engine, these sites will provide even more insight

  • I think that you should add a tenth search engine: Truevert (www.truevert.com). The version on truevert.com is focused on green stuff (environment, sustainability), but it can actually handle any vertical. Adding a new vertical takes less than an hour and is automatic.

    Truevert understands what words mean without having to spend 24 years building an ontology. It understands, for example, that from a green perspective CFL means compact fluorescent light bulbs, not Canadian Football League.

    You might also be interested in some SlideShare presentations on semantic search at https://www.slideshare.net/truevert.

  • I’ve delved a bit deeper (in an admittedly self-serving manner) into the question of how Destination Search Engines can draw attention away from the GooHooSoft tripoly. I could not find a trackback URL here, so I’ve taken the liberty of placing this pointer in comments.

  • I have used many on this list; however, I did not see Semager.com mentioned (a semantic search engine out of Germany). If you know some German, you should look at its analysis page for a website- interesting data there. I like looking into its list of related terms, which allows you to tag surf other aspects of the inquiries meaning.

  • Absolutely great article. One more to dogpile on is Swingly (http://www.swingly.com) — we’re just taking the wraps off now, will be in alpha in May.

  • Search through hundreds of specific search engines, include 35 specific areas like web,music..

  • standle

    http://www.standle.com Search through hundreds of specific search engines, include 35 specific areas like web,music..

  • Cazoodle.com’s Apartment Search yielded 1009 rental classified results in Champaign IL as opposed to Rent.com’s 44. Apartment Search also automatically gives you a map, opens Google Street Map on the same page and gives rent prices, agency information, and links to the agencies website.

  • All these are cool, but essentially have one problem – they are not Google! I’ve commented on this before… their name sound like: haxxorz, megatronzzz, bleptronixx, tekknostile… trying too hard.

    Call it: Bobble or Mio or Banana or ABC instead…

  • offshore

    hey arun another area worth looking at where semantic engines are actually getting a lot of high value users is in the vertical space.

    check out examples like http://www.searchmining.net and http://www.searchpetroleum.net

    these are both vertical and semantic engines and whilst they’re v.niche the give great value to their specific communites

  • The worlds largest and most successful manufacturing companies use Goldfire from Invention Machine. I am surprised you are unaware of Goldfire since it is deployed in hundreds of companies for Semantic Search of both internal and external content.

  • New Search will come from Semantic AND Social. Because Sense cant be handle alone in so many informations

  • Febin

    Did anybody try Semandeks http://semandeks.com , it is in alpha stage though.

  • Bob Franky

    Too be honest – I’m a bigger fan of Dogpile than Google. They support charitable causes and work with all independent search providers to give a good mix of results.

    People are too lazy when it comes to search and want it all to be laid out for them in one engine. Problem is, Google, MSN and Yahoo all pick what shows up where.

    Research is meant to be RESEARCH – so look around for solid results.

    BTW – Dogpile.com just launched a new site called http://www.DoGreatGood.com – and their donating a portion of there revenue to Petfinder and the ASPCA.

    Great that theres a way we can help dog adoption programs at no cost.

  • Andrew

    Interesting article!
    I think the future of search engine is web 2.0 like Mahalo or the italian Ggoal (http://www.ggoal.com)

  • Nice post Arun, Keep it up! ( are u indian? 🙂 if yes, special thanks )

  • New Search will come from Semantic AND Social. Because Sense cant be handle alone in so many informations Cheap Louis Vuitton

  • Very informative post Arun! waiting for the other ones

  • Interesting article!

  • Interesting to know about all those semantic engines!

    However as it’s said before, I don’t see people leaving Google to use any of these engines. Google’s algorithm is much advanced than a single LSI concept and returns far superior results.

    Look at its PageRank technology which itself considers 500 million variables and 2 billion terms.

    Absolutely no competition there.

  • Gregman2

    Yebol is better than Bing (formerly Powerset). Check it out: http://www.yebol.com

  • I agree that semantic search would be good. But I did a quick visit to the above sites, and even though they produced some results on certain situations, they are no good most of the instances.

    I see the results for my keywords much better in Google than any one of them mentioned above.

  • I like the powerset wikipedia article search. It certainly cuts down the time from having to search for the right article. I havent given the others a test drive as ye but might have to have a look. Thanks

  • Intelegencia

    Great Article…I am surprised you are unaware of Goldfire since it is deployed in hundreds of companies for Semantic Search of both internal and external content.


  • Intelegencia

    Great Article…I am surprised you are unaware of Goldfire since it is deployed in hundreds of companies for Semantic Search of both internal and external content.


  • Of course I have come in late here and have the benefit of hindsight but it appears none of the above have had any significant impact on search. I once thought Rockmelt was going to be massive also but it has failed to gain any significant piece of the search market.