WSDM 2018 JAY PUJARA AND SAMEER SINGH Introducing Presenters
Jay Pujara: Research Scientist at USC/ISI
Sameer Singh: Assistant Professor at UCI
2 Tutorial Overview https://kgtutorial.github.io
3 Tutorial Overview https://kgtutorial.github.io Part 1: Knowledge Graphs
4 Tutorial Overview https://kgtutorial.github.io Part 1: Knowledge Graphs
Part 2: Knowledge Extraction
5 Tutorial Overview https://kgtutorial.github.io Part 1: Knowledge Graphs
Part 2: Part 3: Knowledge Graph Extraction Construction
6 Tutorial Overview https://kgtutorial.github.io Part 1: Knowledge Graphs
Part 2: Part 3: Knowledge Graph Extraction Construction
Part 4: Critical Analysis
7 Tutorial Overview https://kgtutorial.github.io Part 1: Knowledge Graphs
Part 2: Part 3: Knowledge Graph Extraction Construction
Part 4: Critical Analysis
8 Tutorial Overview https://kgtutorial.github.io Part 1: Knowledge Graphs
Part 2: Part 3: Knowledge Extraction Graph Construction
Part 4: Critical Analysis
9 Tutorial Outline 1. Knowledge Graph Primer [Jay] 2. Knowledge Extraction Primer [Jay] 3. Knowledge Graph Construction a. Probabilistic Models [Jay] Coffee Break b. Embedding Techniques [Sameer] 4. Critical Overview and Conclusion [Sameer]
10 What if I have a question?
11 Tutorial Overview
Part 1: Knowledge Graphs
Part 2: Part 3: Knowledge Graph Extraction Construction
Part 4: Critical Analysis
12 Knowledge Graph Primer TOPICS: WHAT IS A KNOWLEDGE GRAPH? WHY ARE KNOWLEDGE GRAPHS IMPORTANT? WHERE DO KNOWLEDGE GRAPHS COME FROM? KNOWLEDGE REPRESENTATION CHOICES PROBLEM OVERVIEW
13 Knowledge Graph Primer TOPICS: WHAT IS A KNOWLEDGE GRAPH? WHY ARE KNOWLEDGE GRAPHS IMPORTANT? WHERE DO KNOWLEDGE GRAPHS COME FROM? KNOWLEDGE REPRESENTATION CHOICES PROBLEM OVERVIEW
14 What is a knowledge graph?
15 What is a knowledge graph? • Knowledge in graph form!
16 What is a knowledge graph? • Knowledge in graph form!
• Captures entities, attributes, and relationships
17 What is a knowledge graph? • Knowledge in graph form!
E1 • Captures entities, attributes, and relationships
E2 • Nodes are entities
E3
18 What is a knowledge graph? • Knowledge in graph form!
A1 E 1 A2 • Captures entities, attributes, and relationships
E2
• Nodes are entities A1 A • Nodes are labeled with 2 attributes (e.g., types) E3 A1 A3
19 What is a knowledge graph? • Knowledge in graph form!
A1 E 1 A2 • Captures entities, attributes, and relationships
E2
• Nodes are entities A1 A • Nodes are labeled with 2 attributes (e.g., types) E3 A1 • Typed edges between two A2 nodes capture a relationship between entities
20 Example knowledge graph •
Knowledge in graph form! person John Lennon • Captures entities, attributes, and relationships band Beatles • Nodes are entities • Nodes are labeled with attributes (e.g., types) place Liverpool • Typed edges between two nodes capture a relationship between entities
21 Knowledge Graph Primer TOPICS: WHAT IS A KNOWLEDGE GRAPH? WHY ARE KNOWLEDGE GRAPHS IMPORTANT? WHERE DO KNOWLEDGE GRAPHS COME FROM? KNOWLEDGE REPRESENTATION CHOICES PROBLEM OVERVIEW
22 Why knowledge graphs? • Humans: •Combat information overload •Explore via intuitive structure •Tool for supporting knowledge-driven tasks
• AIs: •Key ingredient for many AI tasks •Bridge from data to human semantics •Use decades of work on graph analysis
23 Applications 1: QA/Agents
24 Applications 2: Decision Support
25 Applications 3: Fueling Discovery
26 Knowledge Graphs & Industry
•Google Knowledge Graph • Google Knowledge Vault •Amazon Product Graph •Facebook Graph API •IBM Watson •Microsoft Satori • Project Hanover/Literome •LinkedIn Knowledge Graph •Yandex Object Answer •Diffbot, GraphIQ, Maana, ParseHub, Reactor Labs, SpazioDati
27 Knowledge Graph Primer TOPICS: WHAT IS A KNOWLEDGE GRAPH? WHY ARE KNOWLEDGE GRAPHS IMPORTANT? WHERE DO KNOWLEDGE GRAPHS COME FROM? KNOWLEDGE REPRESENTATION CHOICES PROBLEM OVERVIEW
28 Where do knowledge graphs come from?
29 Where do knowledge graphs come from?
• Structured Text ◦ Wikipedia Infoboxes, tables, databases, social nets
30 Where do knowledge graphs come from?
• Structured Text ◦ Wikipedia Infoboxes, tables, databases, social nets • Unstructured Text ◦ WWW, news, social media, reference articles
31 Where do knowledge graphs come from?
• Structured Text ◦ Wikipedia Infoboxes, tables, databases, social nets • Unstructured Text ◦ WWW, news, social media, reference articles • Images
32 Where do knowledge graphs come from?
• Structured Text ◦ Wikipedia Infoboxes, tables, databases, social nets • Unstructured Text ◦ WWW, news, social media, reference articles • Images
• Video ◦ YouTube, video feeds
33 Knowledge Graph Primer TOPICS: WHAT IS A KNOWLEDGE GRAPH? WHY ARE KNOWLEDGE GRAPHS IMPORTANT? WHERE DO KNOWLEDGE GRAPHS COME FROM? KNOWLEDGE REPRESENTATION CHOICES PROBLEM OVERVIEW
34 Hayes&McCarthy Brooks Frame Problem Subsumption Quillian ConceptNet Minsky, Filmore Semantic Frames Networks McCarthy Formalizing Commonsense Description Bobrow Logic STUDENT Simon&Newell General Problem Solver Lenant Winograd Cyc SHRDLU
2000 1990 1980 1970 1960 1950 1940
SHRUTI
Rumelhart et al Series of Neural- BackPropagation Symbolic Models Minsky &Pappert McCulloch Systematicity “Perceptrons” &Pitts Debate Artificial Neurons SLIDE COURTESY OF DANIEL KHASHABI Knowledge Representation •Decades of research into knowledge representation
•Most knowledge graph implementations use RDF triples •
•ABox (assertions) versus TBox (terminology)
•Common ontological primitives • rdfs:domain, rdfs:range, rdf:type, rdfs:subClassOf, rdfs:subPropertyOf, ... • owl:inverseOf, owl:TransitiveProperty, owl:FunctionalProperty, ...
36 Semantic Web •Standards for defining and exchanging knowledge • RDF, RDFa, JSON-LD, schema.org • RDFS, OWL, SKOS, FOAF
•Annotated data provide critical resource for automation
•Major weakness: annotate everything?
"LINKING OPEN DATA CLOUD DIAGRAM 2014, BY MAX SCHMACHTENBERG, CHRISTIAN BIZER, ANJA JENTZSCH AND RICHARD CYGANIAK. HTTP://LOD-CLOUD.NET/" 37 Information Extraction from Text •Focus of this tutorial!
•Answer to the knowledge acquisition bottleneck
•Many challenges: • chunking • polysemy/word sense disambiguation • entity coreference • relational extraction
38 Knowledge Graph Primer TOPICS: WHAT IS A KNOWLEDGE GRAPH? WHY ARE KNOWLEDGE GRAPHS IMPORTANT? WHERE DO KNOWLEDGE GRAPHS COME FROM? KNOWLEDGE REPRESENTATION CHOICES PROBLEM OVERVIEW
39 What is a knowledge graph? • Knowledge in graph form!
A1 E 1 A2 • Captures entities, attributes, and relationships
E2
• Nodes are entities A1 A • Nodes are labeled with 2 attributes (e.g., types) E3 A1 • Typed edges between two A2 nodes capture a relationship between entities
40 Basic problems
A1 E 1 A2
E2
A1 A2
E3 A1 A2
41 Basic problems
A1 E • Who are the entities 1 A2 (nodes) in the graph?
E2
A1 A2
E3 A1 A2
42 Basic problems
A1 E • Who are the entities 1 A2 (nodes) in the graph?
• What are their attributes E2 and types (labels)? A1 A2
E3 A1 A2
43 Basic problems
A1 E • Who are the entities 1 A2 (nodes) in the graph?
• What are their attributes E2 and types (labels)? A1 A2 • How are they related E3 (edges)? A1 A2
44 Basic problems
A1 E • Who are the entities 1 A2 (nodes) in the graph?
• What are their attributes E2 and types (labels)? A1 A2 • How are they related E3 (edges)? A1 A2
45 Knowledge Graph Construction
Knowledge Graph Extraction Construction
46 Two perspectives Knowledge Extraction Graph Construction • Who are the entities • Who are the entities (nodes) in the graph? (nodes) in the graph? • Named Entity Recognition • Entity Linking • Entity Coreference • Entity Resolution
• What are their attributes • What are their attributes and types (labels)? and types (labels)? • Named Entity Recognition • Collective Classification
• How are they related • How are they related (edges)? (edges)? • Relation Extraction • Link Prediction • Semantic Role Labeling
47 Tutorial Outline 1. Knowledge Graph Primer [Jay] 2. Knowledge Extraction Primer [Jay] 3. Knowledge Graph Construction a. Probabilistic Models [Jay] Coffee Break b. Embedding Techniques [Sameer] 4. Critical Overview and Conclusion [Sameer]
48