Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
The Mushroom Effect
Or Why You Need Knowledge Graphs for Dialogue Systems
Dr. Michael Galkin
Fraunhofer IAIS & Smart Data Analytics
Dresden
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Outline
Background
Mushrooms?
With KG Flavors
About us: CEE AI Dresden
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Background
We build conversational AI platforms
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Background
We build conversational AI platforms
Powered by knowledge graphs
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Background
We build conversational AI platforms
Powered by knowledge graphs
Obtained by integrating heterogeneous data
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Mushrooms?
Berlin Hbf
What is this building? Q
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Mushrooms?
Berlin Hbf
What is this building? Q
This is Berlin HauptbahnhofA
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Mushrooms?
What is this building? Q
This is Berlin HauptbahnhofA
What is its architectural style? Q
Berlin Hbf
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
What is its architectural style?
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
What is its architectural style?
Wikipedia
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
What is its architectural style?
SQuAD
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
What is its architectural style?
MS MARCO
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
What is its architectural style?
HotPot QA
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Mushrooms!
What is this building? Q
This is Berlin HauptbahnhofA
What is its architectural style? Q
MushroomA
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Mushrooms! What is its architectural style? Q
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Mushrooms! What is its architectural style? Q
✓ its = Berlin Hauptbahnhof
✓ In Berlin
✓ Concept ~ Style
❌ Applicable to the city concept, not
architectural style of the station
❌ Close, but not correct
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
With KG flavors
Can mushrooms be
an architectural
style?
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
With KG flavors
Can mushrooms be
an architectural
style?
Probably not
If not, what can be
an appropriate
value?
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
So why you need graphs?
Implicit or explicit constraints on produced answersHow many children
does Berlin Hbf have?
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
So why you need graphs?
Implicit or explicit constraints on produced answers
- reduce candidates space
- help to fight the mushroom effect
- ontologies help
How many children
does Berlin Hbf have?
Train stations
don’t have kids
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
So why you need graphs?
Implicit or explicit constraints on produced answers
- reduce candidates space
- help to fight the mushroom effect
- ontologies help
Complex QA via (sub)graphs aggregations
What is the busiest
train station in
Germany?
How many children
does Berlin Hbf have?
Train stations
don’t have kids
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
So why you need graphs?
Implicit or explicit constraints on produced answers
- reduce candidates space
- help to fight the mushroom effect
- ontologies help
Complex QA via (sub)graphs aggregations
What is the busiest
train station in
Germany?
select ?station ?visits where {
?station wdt:P31 wd:Q18543139 . # central stations
?station wdt:P17 wd:Q183 . # in Germany
?station wdt:P1373 ?visits . # daily visits
} ORDER BY DESC(?visits) LIMIT 1 # sort
How many children
does Berlin Hbf have?
Train stations
don’t have kids
Hamburg Hbf
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
So why you need graphs?
Graphs significantly improve reasoning
compared to sole natural language inference
Takeaway 1
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
So why you need graphs?
Graphs significantly improve reasoning
compared to sole natural language inference
Reasoning outcomes are explainable and
traceable
Takeaway 1
Takeaway 2
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
KDDS
Knowledge-driven
in-car dialogue
system (EN/DE)
Full DBpedia
2019 (wikidata
branch)
> 50M entities
> 4B triples
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
KDDS @
Hannover-Messe
Building KGs from enterprise
sources is still a challenge
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
KDDS @
Hannover-Messe
Building KGs from enterprise
sources is still a challenge
Depth of knowledge vs
variety of domains
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
KDDS @
Hannover-Messe
Building KGs from enterprise
sources is still a challenge
Depth of knowledge vs
variety of domains
Explainability is crucial
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Fraunhofer IAIS
Standort Dresden
ML2R
National Competence Center for
Machine Learning Rhein-Ruhr
Fraunhofer-Alliance Big Data AI
The biggest Fraunhofer alliance
with > 30 institutes led by IAIS
AI4EU
EU Lighthouse
Project for AI
International Data Spaces
Association
Data sovereignty for Big
Data and AI, 100+
companies
CEE AI
Center for Explainable and Efficient AI
Technologies with TU Dresden
Fraunhofer Center for
Machine Learning
IAIS-led part of Fraunhofer
Cluster of Excellence
Cognitive Internet
Technologies
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Fraunhofer IAIS Dresden
Center for Efficient and Explainable AI
Prof. FitzekProf. Lehmann
● Efficient AI
○ Hardware and software are usually
decoupled instead of embedded
○ 100-times more energy efficient by 2030
● Explainable AI
○ Make AI more traceable
○ Make AI decisions more explainable
Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019
Center for Explainable and Efficient AI

More Related Content

PDF
GeniusTex - a Smart Textiles innovation platform with semantic technologies i...
PDF
Präsentation der Semantic Web Lehrkonzepte an der TH Brandenburg
PDF
Semantic Web in the Digital Humanities
PDF
Knowledge Graphs for Scholarly Communication
PDF
Das QROWD-Projekt - Because Big Data Integration is Humanly Possible
PDF
An Ontology Engineering Approach to Support Personalized Gamification of CSCL
PDF
The DBpedia databus
PDF
tech4comp - Kompetenzmessung durch Datenanalyse für E-Assessment
GeniusTex - a Smart Textiles innovation platform with semantic technologies i...
Präsentation der Semantic Web Lehrkonzepte an der TH Brandenburg
Semantic Web in the Digital Humanities
Knowledge Graphs for Scholarly Communication
Das QROWD-Projekt - Because Big Data Integration is Humanly Possible
An Ontology Engineering Approach to Support Personalized Gamification of CSCL
The DBpedia databus
tech4comp - Kompetenzmessung durch Datenanalyse für E-Assessment

More from Leipziger Semantic Web Tag (9)

PDF
PlatonaM - Plattform-Ökosystem for innovative maintenance management through ...
PDF
xCOR - a Value Chain Framework Ontology
PDF
Linked Data Publication Pipelines for Agri-Related use cases
PDF
Das LIMBO Projekt – Linked Data Enterprise Use-Cases unter Verwendung der Dat...
PDF
SNIK: An Ontology of Information Management in Hospitals
PDF
The WUMM Project Semantic Data and Innovation Management
PDF
BEXIS 2 - Semantic Web Techniques in Research Data Management
PDF
Towards a productive Linked Data environment within Enterprises
PlatonaM - Plattform-Ökosystem for innovative maintenance management through ...
xCOR - a Value Chain Framework Ontology
Linked Data Publication Pipelines for Agri-Related use cases
Das LIMBO Projekt – Linked Data Enterprise Use-Cases unter Verwendung der Dat...
SNIK: An Ontology of Information Management in Hospitals
The WUMM Project Semantic Data and Innovation Management
BEXIS 2 - Semantic Web Techniques in Research Data Management
Towards a productive Linked Data environment within Enterprises
Ad

Recently uploaded (20)

PDF
How ambidextrous entrepreneurial leaders react to the artificial intelligence...
PDF
TrustArc Webinar - Click, Consent, Trust: Winning the Privacy Game
PDF
Developing a website for English-speaking practice to English as a foreign la...
PDF
ENT215_Completing-a-large-scale-migration-and-modernization-with-AWS.pdf
PDF
CloudStack 4.21: First Look Webinar slides
PPTX
Final SEM Unit 1 for mit wpu at pune .pptx
PDF
STKI Israel Market Study 2025 version august
PDF
A comparative study of natural language inference in Swahili using monolingua...
PDF
Architecture types and enterprise applications.pdf
PDF
Zenith AI: Advanced Artificial Intelligence
PPTX
Group 1 Presentation -Planning and Decision Making .pptx
PPTX
Modernising the Digital Integration Hub
PDF
Five Habits of High-Impact Board Members
PDF
Enhancing emotion recognition model for a student engagement use case through...
PDF
Taming the Chaos: How to Turn Unstructured Data into Decisions
PDF
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
PDF
1 - Historical Antecedents, Social Consideration.pdf
PPTX
Web Crawler for Trend Tracking Gen Z Insights.pptx
PDF
Transform Your ITIL® 4 & ITSM Strategy with AI in 2025.pdf
PDF
WOOl fibre morphology and structure.pdf for textiles
How ambidextrous entrepreneurial leaders react to the artificial intelligence...
TrustArc Webinar - Click, Consent, Trust: Winning the Privacy Game
Developing a website for English-speaking practice to English as a foreign la...
ENT215_Completing-a-large-scale-migration-and-modernization-with-AWS.pdf
CloudStack 4.21: First Look Webinar slides
Final SEM Unit 1 for mit wpu at pune .pptx
STKI Israel Market Study 2025 version august
A comparative study of natural language inference in Swahili using monolingua...
Architecture types and enterprise applications.pdf
Zenith AI: Advanced Artificial Intelligence
Group 1 Presentation -Planning and Decision Making .pptx
Modernising the Digital Integration Hub
Five Habits of High-Impact Board Members
Enhancing emotion recognition model for a student engagement use case through...
Taming the Chaos: How to Turn Unstructured Data into Decisions
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
1 - Historical Antecedents, Social Consideration.pdf
Web Crawler for Trend Tracking Gen Z Insights.pptx
Transform Your ITIL® 4 & ITSM Strategy with AI in 2025.pdf
WOOl fibre morphology and structure.pdf for textiles
Ad

Mushroom Effect or Why You Need Knowledge Graphs for Dialogue Systems

  • 1. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 The Mushroom Effect Or Why You Need Knowledge Graphs for Dialogue Systems Dr. Michael Galkin Fraunhofer IAIS & Smart Data Analytics Dresden
  • 2. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Outline Background Mushrooms? With KG Flavors About us: CEE AI Dresden
  • 3. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Background We build conversational AI platforms
  • 4. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Background We build conversational AI platforms Powered by knowledge graphs
  • 5. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Background We build conversational AI platforms Powered by knowledge graphs Obtained by integrating heterogeneous data
  • 6. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Mushrooms? Berlin Hbf What is this building? Q
  • 7. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Mushrooms? Berlin Hbf What is this building? Q This is Berlin HauptbahnhofA
  • 8. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Mushrooms? What is this building? Q This is Berlin HauptbahnhofA What is its architectural style? Q Berlin Hbf
  • 9. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 What is its architectural style?
  • 10. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 What is its architectural style? Wikipedia
  • 11. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 What is its architectural style? SQuAD
  • 12. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 What is its architectural style? MS MARCO
  • 13. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 What is its architectural style? HotPot QA
  • 14. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Mushrooms! What is this building? Q This is Berlin HauptbahnhofA What is its architectural style? Q MushroomA
  • 15. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Mushrooms! What is its architectural style? Q
  • 16. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Mushrooms! What is its architectural style? Q ✓ its = Berlin Hauptbahnhof ✓ In Berlin ✓ Concept ~ Style ❌ Applicable to the city concept, not architectural style of the station ❌ Close, but not correct
  • 17. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 With KG flavors Can mushrooms be an architectural style?
  • 18. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 With KG flavors Can mushrooms be an architectural style? Probably not If not, what can be an appropriate value?
  • 19. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 So why you need graphs? Implicit or explicit constraints on produced answersHow many children does Berlin Hbf have?
  • 20. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 So why you need graphs? Implicit or explicit constraints on produced answers - reduce candidates space - help to fight the mushroom effect - ontologies help How many children does Berlin Hbf have? Train stations don’t have kids
  • 21. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 So why you need graphs? Implicit or explicit constraints on produced answers - reduce candidates space - help to fight the mushroom effect - ontologies help Complex QA via (sub)graphs aggregations What is the busiest train station in Germany? How many children does Berlin Hbf have? Train stations don’t have kids
  • 22. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 So why you need graphs? Implicit or explicit constraints on produced answers - reduce candidates space - help to fight the mushroom effect - ontologies help Complex QA via (sub)graphs aggregations What is the busiest train station in Germany? select ?station ?visits where { ?station wdt:P31 wd:Q18543139 . # central stations ?station wdt:P17 wd:Q183 . # in Germany ?station wdt:P1373 ?visits . # daily visits } ORDER BY DESC(?visits) LIMIT 1 # sort How many children does Berlin Hbf have? Train stations don’t have kids Hamburg Hbf
  • 23. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 So why you need graphs? Graphs significantly improve reasoning compared to sole natural language inference Takeaway 1
  • 24. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 So why you need graphs? Graphs significantly improve reasoning compared to sole natural language inference Reasoning outcomes are explainable and traceable Takeaway 1 Takeaway 2
  • 25. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 KDDS Knowledge-driven in-car dialogue system (EN/DE) Full DBpedia 2019 (wikidata branch) > 50M entities > 4B triples
  • 26. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 KDDS @ Hannover-Messe Building KGs from enterprise sources is still a challenge
  • 27. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 KDDS @ Hannover-Messe Building KGs from enterprise sources is still a challenge Depth of knowledge vs variety of domains
  • 28. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 KDDS @ Hannover-Messe Building KGs from enterprise sources is still a challenge Depth of knowledge vs variety of domains Explainability is crucial
  • 29. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Fraunhofer IAIS Standort Dresden ML2R National Competence Center for Machine Learning Rhein-Ruhr Fraunhofer-Alliance Big Data AI The biggest Fraunhofer alliance with > 30 institutes led by IAIS AI4EU EU Lighthouse Project for AI International Data Spaces Association Data sovereignty for Big Data and AI, 100+ companies CEE AI Center for Explainable and Efficient AI Technologies with TU Dresden Fraunhofer Center for Machine Learning IAIS-led part of Fraunhofer Cluster of Excellence Cognitive Internet Technologies
  • 30. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Fraunhofer IAIS Dresden Center for Efficient and Explainable AI Prof. FitzekProf. Lehmann ● Efficient AI ○ Hardware and software are usually decoupled instead of embedded ○ 100-times more energy efficient by 2030 ● Explainable AI ○ Make AI more traceable ○ Make AI decisions more explainable
  • 31. Michael Galkin 7. Leipziger Semantic Web Tag 22.05.2019 Center for Explainable and Efficient AI