Good Bye Knowledge Graph, Hello Google Knowledge Vault?

by Posted @ Aug 25 2014


The KDD 2014 Conference Home Page

The Knowledge Vault Was Recently Announced

This morning, at the 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Google may announce that they are trying a new approach with a knowledge base, applying a mix of technologies to automate a lot of the collection of information that helps in:

  • Fueling efforts at Google to present more and better knowledge panel results
  • Helping Google recognize entities (specific people, place and things) within queries
  • Making predictive algorithms for personal assistants such as Google Now & Siri & Cortana smarter and more assistive
  • Bringing Us New Applications and Undiscovered Uses

The announcement carries with it a lot of new information about approaches Google follows to deliver more information to people faster, in a more complete form. Before you delve too quickly into this topic, reading the following paper (PDF) from Google is highly recommended:

Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion.

The Knowledge Vault Was An Effort to Get Knowledge Base Information to Scale Better

At the Semantic Web Conference, a common theme in presentations from search engineers such as Google Fellow Ramanathan Guha was the importance of getting knowledge base information to scale better and help applications from rich snippets to knowledge panels, to mobile apps, and others. These many different kinds of applications need to be able to use such information, and the more information that is available, the more effective they will be.

For example, there have been medical studies conducted by organizations for the US Government where the conclusions have been online, but the data itself from the studies haven’t been shared. It’s a shame that knowledge isn’t shared in a way that could help others.

The new Knowledge Vault doesn’t have as much information as Google’s Freebase knowledge base. Freebase has 637M (non-redundant) facts, and the Knowledge Vault has only 302M “confident” facts. Of that, only 223M are in Freebase. There are many missing values for facts in Freebase entities, with 71% of people in Freebase having no known place of birth, and 75% having no known nationality. But the increase in the “confidence” of facts included in the Knowledge Vault is significant.

Sometimes some problems make creating a Freebase entry difficult.

A Freebase Entry for a Biblical Figure using Bible-based facts.

Google’s been working upon this automated approach to building the Knowledge Vault with greater confidence in the facts it includes, using methods such as:

A detailed presentation for KDD titled Constructing and Mining Web-scale Knowledge Graphs is worth downloading and studying if you want more details.

With this faster-automated approach to building and representing knowledge by Google with the Knowledge Vault, we’re pretty excited by how much more information this can provide to searchers, and how many more opportunities it can bring to site owners.

subscribe to our newsletter


  1. You made a typo: “Of those only 302M are in Freebase.” should be “Of those, 223M are in Freebase” 🙂

  2. Bill Slawski says:

    Hi Jan-Willem.

    Thanks for pointing that out.

    I wanted to really stress that a lot of the facts in Freebase didn’t make it into the Knowledge Vault, so it’s not as if Google just took Freebase and other knowledge base information from elsewhere and just kept it and stitched it together somehow, as I saw someone else report about the Knowledge Vault. 🙁

  3. Amit Roy says:

    That info was out of the world Bill. Really commendable. I have downloaded the paper and also went through the Newscientist blog. Really feeling excited with such inputs to come in near future.

    • Bill Slawski says:

      Thanks, Amit,

      I was really excited to see the many things Google was trying involving the Knowledge Vault, too. The near future looks interesting. 🙂

  4. Oscar says:

    I see everything on your site except the text of this blogpost. I only see the image.

    After I refresh a couple of times I see the text, when I refresh again a couple of times it goes away.

    You should look at it.

  5. […] a high degree of confidence apart from human actions such as markup. Recent announcements about Google’s Knowledge Vault project would seem to reinforce that Google is moving steadily in that direction. So this may be how they […]

  6. […] trusted members of a niche. And while that didn’t work for Authorship, what’s not to say that Google Knowledge Vault won’t deliver that sense of […]

  7. […] how they extract information from the Web. He told me that he had read something I wrote about the Google Knowledge Vault, and how it was aimed at providing results that were more complete and more filled with more […]

  8. […] Good Bye Knowledge Graph, Hello Google Knowledge Vault? – Go Fish Digital, August 25, 2014 […]

  9. […] Last week I retweeted an article I saw in New Scientist, a magazine that doesn’t usually offer insights into things happening at Google. The title of the article caught my eye, Google’s fact-checking bots build vast knowledge bank. I think I noticed it in part because I was spending the week in San Jose, co-presenting …  […]

  10. […] anche Bill Slawski e David Amerland offrono il loro contributo sul tema, il primo con il post “Good Bye Knowledge Graph, Hello Google Knowledge Vault?” e il secondo con Google’s Knowledge Vault is Semantic Search on […]

  11. Bill, Great article, we here are are real interested in biblical search and helping to contribite to the semantic search of the bible and Christian web sites for trustworthy material..

    • Bill Slawski says:

      Thank you, David. There’s a lot of information out there on the Web. Hopefully Semantic Search will be of assistance to you in your efforts to reach out to others and share.

  12. Alex Smith says:


    How can I get Knowledge graph for my Business?

    • Bill Slawski says:

      Hi Alex,

      There are a number of steps that might lead to a Knowledge graph appearing for your business, which could include creating a My Business page at Google and verifying it. If your business fulfills Wikipedia’s Notability requirements, having a Wikipedia page could also potentially help.

  13. […] a number of places on the Web since, including a post I wrote on the Go Fish Digital site titled Good Bye Knowledge Graph, Hello Google Knowledge Vault?, and an article by Gregg Sterling at at Search Engine Land named Google “Knowledge Vault” To […]

Leave a Comment