The Google Knowledge Graph (GKG) is a huge database of information about entities and their relationships. It enhances Google Search by providing summaries of topics, dealing with ambiguous queries, and revealing new facts from sources like Freebase, Wikipedia, and the CIA World Factbook. The GKG represents entities as nodes and relationships as links between them, implementing principles of the Web of Data to transform Google into a knowledge engine.

1. www.sti-innsbruck.at© Copyright 2008 STI INNSBRUCK www.sti-innsbruck.at
The Google Knowledge Graph
Ioan Toma

2. www.sti-innsbruck.at
Agenda
• What is the Google Knowledge Graph (GKG)?
• How it is used?
• Data sources
• The Google Knowledge Graph and the Web of Data
2

3. www.sti-innsbruck.at
What is it?
• “A huge knowledge graph of interconnected entities and their
attributes”.
Amit Singhal, Senior Vice President at Google
• “A knowledge based used by Google to enhance its search engine’s
results with semantic-search information gathered from a wide
variety of sources”
http://en.wikipedia.org/wiki/Knowledge_Graph
3

4. www.sti-innsbruck.at
• Based on information derived from many sources including
Freebase, CIA World Factbook, Wikipedia
• Contains 570 million objects and more than 18 billion facts about
and relationships between these different objects
4
What is it?

5. www.sti-innsbruck.at
GKG enhances Google Search in three main ways:
•Find the right thing
– deals with the ambiguity of the language
5
What is it?

6. www.sti-innsbruck.at
GKG enhances Google Search in three main ways:
•Summaries
– summarize relevant content around that topic, including key facts about the
entity
6
What is it?

7. www.sti-innsbruck.at
GKG enhances Google Search in three main ways:
•Deeper and broader information
– reveal new facts
– anticipate what the next questions and provide the information beforehand
(based on what other users asked before)
7
What is it?

8. www.sti-innsbruck.at 8
How it is used?
• Search for a person, place, or thing
• Facts about entities are displayed in a knowledge box on the right side

9. www.sti-innsbruck.at 9
How it is used?
• Explore your search

10. www.sti-innsbruck.at 10
• CIA World Factbook
• Freebase
• Wikipedia
• and many others …
Data sources

11. www.sti-innsbruck.at 11
GKG and CIA World Factbook
• CIA World Factbook is a reference
resource produced by the Central
Intelligence Agency of the United
States with almanac-style
information about the countries of
the world.
• GKG integrates information about
geography, government, economy,
etc. from CIA World Factbook

12. www.sti-innsbruck.at 12
GKG and Freebase
• Freebase is large collaborative knowledge
base, developed by Metaweb and acquired by
Google in 2010.
• GKG uses UIDs directly from the Freebase;
detective work of Andreas Thalhammer
showing how to get from GKG UIDs to
Freebased UIDs using base64 and gzip
• Check the “Knowledge Graph links to
Freebase” thread on w3c mailinglist
http://lists.w3.org/Archives/Public/semantic-
web/2012Jun/0028.html

13. www.sti-innsbruck.at
• For most search results first sentences come from Wikipedia
13
GKG and Wikipedia

14. www.sti-innsbruck.at 14
Other sources
• GKG also considers the information Google retrieves from the
volume of queries done by the users and the links those users
have clicked on the results presented for those queries

15. www.sti-innsbruck.at 15
GKG and other Google products
• GKG is integrated with other Google products e.g. Google+

16. www.sti-innsbruck.at 16
Web of Data
Hypertext
Hypermedia
Web
Web of Data
Semantic Web
Picture from http://www.theatlantic.com/doc/194507/bush
?
Picture from [4]
“As We May Think”, 1945
Semantic
Annotations

17. www.sti-innsbruck.at 17
Web of Data
• Characteristics:
– Links between arbitrary things
(e.g., persons, locations,
events, buildings)
– Structure of data on Web
pages is made explicit
– Things described on Web
pages are named and get
URIs
– Links between things are
made explicit and are typed
• Web of Data
“Things”
Typed Links

18. www.sti-innsbruck.at
GKG and the Web of Data
• A closed implementation of Web of Data principles
– is not about documents, but objects such as people, places and things
– objects are interlinked in the GKG
– objects have structured information which is obtained from the web
• The Google Knowledge Graph is the basis for transforming Google’
core search product from an information engine to a knowledge
engine (entity search engine)
18

19. www.sti-innsbruck.at
References
• http://www.google.com/insidesearch/features/search/knowledge.html
• http://googleblog.blogspot.co.at/2012/05/introducing-knowledge-graph-
things-not.html
• http://en.wikipedia.org/wiki/Knowledge_Graph
• http://lists.w3.org/Archives/Public/semantic-web/2012Jun/0028.html
• http://www.stateofsearch.com/search-in-the-knowledge-graph-era/
19

20. www.sti-innsbruck.at
Questions?