Google search gets semantic with Knowledge Graph

Google has made its leap into semantic search with the Knowledge Graph, which aims to deliver more relevant search results by taking context into account.

Google has unveiled its Knowledge Graph, a step towards semantic search. Image credit: Google

On Wednesday, Google's head of engineering Amit Singhal described the Knowledge Graph as "a critical first step towards building the next generation of search, which taps into the collective intelligence of the web and understands the world a bit more like people do".

"We've been working on an intelligent model — in geek-speak, a 'graph' — that understands real-world entities and their relationships to one another: things, not strings," Singhal wrote in a blog post.

The end goal is to create "the 'Star Trek computer' that I've always dreamt of building", he added.

The Knowledge Graph is gradually rolling out to all Google users, with those using US English first in line. The company did not say when people in the UK can expect to start seeing it.

The move is part of a broader trend of introducing semantic understanding — in other words, the understanding of meaning — to the web. The idea is to make the user's interaction with the web more like that with humans, where context is understood and natural language can supersede machine-like strings of keywords.

The database underpinning the Knowledge Graph already includes more than 500 million objects and "more than 3.5 billion facts about and relationships between these different objects", Singhal said.

Semantic search in practice

The engineering chief used the example of 'Taj Mahal' to explain what the Knowledge Graph does. Pointing out that the term could apply to the monument, a musician, an Indian restaurant or a casino, he said a search for 'Taj Mahal' would now bring up a range of options in a right-hand sidebar, so users could more quickly help Google to understand what they want.

It's not just a catalogue of objects; it also models all these inter-relationships.

– Amit Singhal, Google

The sidebar also includes factual summaries for the search subject, as well as a portal for clicking through to related people and objects.

Here, Singhal gave the example of Marie Curie. A search for the physicist will bring up her birth and death dates and a summary of her achievements, along with links to searches for her husband Pierre and other scientific contemporaries.

"The Knowledge Graph also helps us understand the relationships between things. Marie Curie is a person in the Knowledge Graph, and she had two children, one of whom also won a Nobel Prize, as well as a husband, Pierre Curie, who claimed a third Nobel Prize for the family," he said. "All of these are linked in our graph."

"It's not just a catalogue of objects; it also models all these inter-relationships. It's the intelligence between these different entities that's the key," Singhal explained.

The Knowledge Graph's summaries and suggestions are drawn from the aggregation of previous searches. For example, it will deliver building design results for architect Frank Lloyd Wright and book results for Charles Dickens, even though Lloyd Wright also had books published.

"The information we show for Tom Cruise answers 37 percent of next queries that people ask about him," Singhal noted.

Google is making a big mobile push around Knowledge Graph, integrating its results into its services for smartphones and tablets running Android 2.2 and higher, or iOS 4 and higher.

"Say I'm searching for 'Andromeda', which could be the galaxy, the TV series or the Swedish band," engineering manager Junyoung Lee wrote in a separate blog post. "The Knowledge Graph distinguishes between each of these meanings and shows me an interactive ribbon at the top of the search results that I can swipe and tap to select just what I'm looking for. That means less typing."

Android users will be able to get Knowledge Graph results through the mobile browser and the Quick Search Box, and iPhone and iPad users through the browser and Google Search App.

The move in context

The Knowledge Graph is the biggest upgrade to Google's core search product in years, with the possible exception of the Google+ integration that took place in January.

It also follows the introduction of Google's new privacy policy, which allows personal data to be shared between all the different Google services that a person uses.

That revision has prompted protests from privacy advocates and EU legislators, who say the company rushed the changes through without due consultation or much of a warning to those who may prefer their Google services not to be linked.

The introduction of the Knowledge Graph also potentially gives Google more of an edge in its competition with Bing, Microsoft's search engine. Bing uses results from the Wolfram Alpha 'knowledge engine', which also aims to understand the context of questions, but only to a limited degree.