A firm that had its origins in Microsoft’s spell check software in the Eighties is the secret sauce behind a new Web 3.0 semantic search engine that could out-search Google in context and relevance.
The Cogito semantic search engine from Expert Systems is designed around the principle of human comprehension to allow content to be understood in the way in which its author intends it to be.
For example, a Google search for the word ‘jaguar’ would pull up content around the animal and the car. But semantic search would not only look at the keyword but also words around it like ‘jungle’ or ‘saloon’ to separate the two meanings.
“Currently, keyword search remains the most popular search technique for users on the public web and corporate intranets,” said Mike David, an analyst with research firm Ovum.
“But many believe its time is up because consumers and business users no longer want to see 30,000 hits on a search and then wade through a list of loosely related keyword results to find relevant documents.
“This is where a new breed of so-called semantic technologies comes into the frame. Unlike ranking algorithms such as Google’s PageRank for predicting relevancy, semantic search dips into the meaning in language to produce highly relevant search results.”
“For example, Expert System provides its own semantic search platform – branded as Cogito (Latin for ‘I think’), and is provided as a fully-hosted service worldwide to offer businesses ‘better search’.”
Davis and his colleague Madan Sheina assert that semantic search is just one of several search techniques that are being forwarded as better and more precise alternatives to keyword search.
Others include heuristics and ontology, linguistics and text mining and also statistical methods.
“Other search engines often hit a brick wall when it comes to deep analysis,” Sheina said. “For example, when a heuristically-driven search engine sees two adjectives in a sentence, it usually washes them out and scores the sentence as neutral because it has no understanding of where the two separate adjectives are pointing.”
The Ovum analysts reckon Expert System can go the extra mile because it has a semantic network – a lexical database that provides a knowledge representation of word definitions and their relationships.
“In essence, it has poured Webster’s dictionary into an in-memory database – comprising 350,000 words and 2.8 million relationships.
Expert System isn’t the only company eyeing the semantic web (currently dubbed ‘Web 3.0’). Other semantic start-ups include Powerset, Yedda, Trovix and Hakia.
Awareness of semantic search rose this summer when Microsoft picked up San Francisco-based Powerset. Interestingly, Microsoft followed that up with its second semantic buy – Zoomix, a data quality provider that has baked semantic self-matching methods into its software.
“Semantic networks are tricky to build and not all are equal,” Davis observed. “However, it’s unlikely that Expert System and other semantic technologies will ever be able to provide 100pc precision in their analysis and results. Moreover, there are still question marks over potentially sticky performance issues with semantic searches that eat up more processing cycles.”
By John Kennedy
Pictured: Semantic searching in the form of Cogito
