Previously here on Search Engine Journal, I covered various Semantic Search Engines which have erupted on the scene as alternatives to Google and Microsoft / Yahoo. Here are 4 more search engines that use different approaches to make results highly relevant.
Evri.com, to put it briefly, presents to you connections between content that goes beyond keyword search. The technology powering the site is able to extract the subjects that occur in an article. This is similar to the approach that people use to understand the meaning of sentences where words and their occurrence in a sentence are used to make sense of the right context.
Taking an example from the Evri Blog,
for a sentence like:
Chief Seattle spoke to his people.
our system recognizes the base subject>verb>object grammatical clause to be Seattle>speak>people. In addition, our system knows that cities do not typically speak to people whereas people do. Our system also recognizes Chief to be the prefix modifier of Seattle, as well as a title used to address a human. This understanding enables our system to recognize Seattle, in this sentence, as a person.
In addition, the other cool features from the site are :
- EvriFeed, a constantly updating stream of the latest about interesting topics in the EvriVerse.
- Evribot, an automated Twitter account that tweets extremely brief summaries of news stories.
- Collections allow you to follow entities for latest updates on them.
- APIs to make these entity extraction available to Developers
- There is an iphone app as well.
Using semantic technologies, Evri is able to search, relate and suggest information beyond the limits of keyword matching. Perhaps the icing on the cake would be providing completely crafted articles that get their information from the ever growing content on the web, but are not being heavily dependent on any single source alone.
DuckDuckGo.com – this search engine does best to save you from spam search results and also provides content summary, zero click information and query disambiguation (one word meaning different things). What has impressed me about this site is the quality of search results. There are good articles that I have come across that are not directly related to the search query but provide lot of information relevant to the domain that the query belongs to.
There is a firefox extension for the engine that saves you from useless, parked and spam pages from search results, They have an iPhone app as well.
DeepDyve is a research tool that retrieves content from the ‘Deep Web‘. By applying semantics to a data source not indexed by traditional search engines, the engine has a good chance of returning very relevant data. For now, the engine is limited to these areas :
- Life Sciences and Medical
- Physical Sciences
- Humanities and Social Sciences
- Business and Finance
- Patents, Legal
- Clean Technology and Energy
- IT and Engineering.
If you need specific information in any of these areas, you must try DeepDyve.
Truevert claims a semantic model that is not dependent on categorization alone. While the engine presently serves content in context of the environment, the idea is to have a model created for different contexts that a keyword can map to. Their blog provides good information on semantic search and the different approaches. The contextual model makes for highly scalable and quick response times.
Each of the above search engines use different approaches to solve the same problem – making search relevant, fast and clean. Do give them a try and let us know your comments.