Professional Documents
Culture Documents
Semantic Network and Knowledge Graph
Semantic Network and Knowledge Graph
&
Knowledge Graph
Logic for Artificial Intelligence
Yi Zhou
Content
• Semantic network
• Frame system
• Knowledge graph
• Knowledge base construction
• Knowledge base completion
• Conclusion
2
Content
• Semantic network
• Frame system
• Knowledge graph
• Knowledge base construction
• Knowledge base completion
• Conclusion
3
Semantic Network
ConceptNet5
Content
• Semantic network
• Frame system
• Knowledge graph
• Knowledge base construction
• Knowledge base completion
• Conclusion
6
Frame System
Frame
• Facts or Data
Values (called facets)
• Procedures
IF-NEEDED : deferred evaluation
IF-ADDED : updates linked information
• Default Values
For Data
For Procedures
• Other Frames or Subframes
Frame System - Example
Slot Value Type
ALEX _ (This Frame)
NAME Alex (key value)
ISA Boy (parent frame)
SEX Male (inheritance value)
IF-NEEDED:
AGE Subtract(current,BIRTHD (procedural attachment)
ATE);
HOME 100 Main St. (instance value)
BIRTHDATE 8/4/2000 (instance value)
FAVORITE_FOOD Spaghetti (instance value)
CLIMBS Trees (instance value)
BODY_TYPE Wiry (instance value)
NUM_LEGS 1 (exception)
Frame Systems
Content
• Semantic network
• Frame system
• Knowledge graph
• Knowledge base construction
• Knowledge base completion
• Conclusion
10
Google Knowledge Graph
• “A huge knowledge graph of interconnected entities and their
attributes”.
Amit Singhal, Senior Vice President at Google
11
Sources
• 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
12
How to use
GKG enhances Google Search in three main ways:
•Find the right thing
– deals with the ambiguity of the language
13
How to use
GKG enhances Google Search in three main ways:
•Summaries
– summarize relevant content around that topic, including key facts about the
entity
14
How to use
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)
15
How it is used?
16
How it is used?
17
Data sources
• Freebase
• Wikipedia
18
GKG and CIA World Factbook
19
GKG and Freebase
20
GKG and Wikipedia
21
Other sources
22
GKG and other Google products
23
WebWeb
ofofData
Data
Semantic Web
Picture from [4]
? Semantic
Web
Annotations
Hypermedia
Hypertext
25
Knowledge Base Construction
• Crowdsourcing from experts
openCyc, snomed
• Crowdsourcing from non-experts
Freebase, wikidata
• Interactive games
conceptNet
• Automated construction from semi-structured data
data mining
• Automated construction from semi-structured data
Google’s knowledge graph, DBpedia
• Automated construction from unstructured data
Deepdive, openIE
Knowledge Bases
OpenCYC, WordNet, FrameNet, ConceptNet, Verbnet,
Freebase, Google knowledge graph/vault, BabelNet,
YAGO, DBpedia, WikiData, Wiktionary, OMICS,
WikiHow, ProBase/ConceptGraph, SNOMED… …
Content
• Semantic network
• Frame system
• Knowledge graph
• Knowledge base construction
• Knowledge base completion
• Conclusion
28
Knowledge Base Completion
Distributed representation
Beijing = [0,0,0,1,0,1,0,0,1,0,0]
China = [0,0,1,1,1,0,0,0,1,0,0]
Sim(Beijing,China)=0.84
Head, Relation, Tail
Knowledge structured as graph
–Eachnode=anentity
–Eachedge=arelation
Fact: (head,relation,tail)
–head=subjectentity
–relation=relationtype
–tail=objectentity
TypicalKGs
–WordNet:LinguisticKG
–Freebase:WorldKG
TransE
For each triple (head, relation, tail), relation as a translation from head to tail
33
Conclusion
Semantic network for representation
Google’s knowledge graph
Knowledge base construction for learning
Knowledge base completion for reasoning
Thank you!