SlideShare a Scribd company logo
1 of 71
KI – Institute for Artificial Intelligence
Knowledge graphs for
knowing more and knowing for sure
Steffen Staab
@ststaab
https://www.ki.uni-stuttgart.de
https://semanux.com
https://southampton.ac.uk/research/institutes-centres/web-internet-science
provides an international forum for presentation and
discussion of research on information and knowledge
management, as well as recent advances on data and
knowledge bases.
2
Conference on Information and Knowledge Management
Rather: Conference on Large Language Models?
Let’s explore the role of knowledge bases/graphs!
1. What is a Knowledge Graph?
2. Some Applications of Knowledge Graphs
3. Knowledge Graphs for Knowing for Sure
4. Knowledge Graphs for Knowing More
5. Large Language Models as Knowledge Bases
6. Large Language Models as AI Assistants
3
Plan for my talk
1 What is a
Knowledge Graph?
What is a Knowledge Graph?
A model for knowledge structures with
5
C22.0
Patient2342
treatedBy
„liver tumor“ / „PhValue 7.5“
Concepts
Entities
Relations
Labels / Values
Queries
• Scalability to
billions of facts
• Answering with
• facts
• predictions
• recommendations
6
What does a knowledge graph do for us?
What are the difficulties?
Example from medical project:
• Foundational Model of Anatomy:
75.000 concepts, 120.000 labels,
> 2 Mio facts
• Not even patient data yet!
Queries
Ontologies & Facts
• How to develop and integrate
ontologies?
• How to provide facts?
• Reasoning?
• Learning?
• Guarantees?
7
What does a knowledge graph do for us?
What are the difficulties?
Example from medical project:
• Foundational Model of Anatomy
• RadLex
• ICD-10
Queries
Ontologies & Facts
What can be represented?
• Provenance
• Uncertainty
• Time
• …
8
What does a knowledge graph do for us?
What are the difficulties?
Example from medical project:
• Patient history
• patient measurements
2 Some Applications
of Knowledge
Graphs
02.11.2020
Steffen Staab, Universität Stuttgart, @ststaab, https://www.ipvs.uni-stuttgart.de/departments/ac/ 10
Encyclopedic
Knowledge Graph
02.11.2020
Steffen Staab, Universität Stuttgart, @ststaab, https://www.ipvs.uni-stuttgart.de/departments/ac/ 11
Wonderful ressource
– but not representative
12
Application 1: Bosch Semantic Stack
©
Kalaycı, Elem Güzel, et al. "Semantic integration of Bosch manufacturing data using virtual knowledge graphs." ISWC 2020: 19th International
Semantic Web Conference, Springer, 2020.
Application 2: KG for Circular Factory
Product
Production
Co-
Design
Knowledge Graph contains knowledge about design, production and product
including plans, sensor measurements and intra-logistics
14
Application 3: Architecture, Engineering, Construction
[CAAD Futures 2023] Collaboration with architects Happold, London
https://pixabay.com/de/users/peggy_marco-1553824/
KG-S
Simul
structural
engineering
KG-A
Design
architectural
design
KG-C
Constr
construction
customer requirements
acoustic engineering
electrical engineering
ventilation
fire containment
plumbing
….
many stakeholders
many tools
work in parallel, no waterfall
mutual dependencies
KG-A
Design
architectural
design
many stakeholders
many tools
work in parallel, no waterfall
mutual dependencies
code as agent
https://vimeo.com/372594657
• Updates and deletions with dependencies [EKAW18],
also at the ontological level [KR2020]
• Federation [WWW08]
• Lacking views with deletions and updates
• Transaction locking [ESWC2013]
• Lacking recent standards (SHACL) and optimistic schemes
• Uncertainties
• Managing identities
(„does re-designed column preserve its identity?“)
• ...
17
Applications Imply Wealth of Requirements
rudimentary
available
research
Encyclopedic KGs
• Facts are reported often
• Who is Douglas Adams?
• What is the capital of France?
• Head of distribution of world
knowledge on the Web
• Answers with high precision
retrieval desired
Engineering KGs
• Point facts exist once
• w3476 instOf AngleGrinder
• faceGear4223
maxDeviation 0.3mm
• Processes are important
• Answers must be correct
18
Sliding scale of knowledge graph requirements
Currently fashionable
research
“we build a system”
under-researched
A lot of research in Knowledge Graphs builds on the
assumption that we want to query encyclopedias
but we have many other requirements in industry.
19
Observation 1
3 Knowing for Sure
KG 1 KG 2 KG 3
App A App B App C
Scenario in Architecture, Engineering, Construction
(AEC)
22
SOLID Project
https://solidproject.org/
• people store their data
securely in decentralized
data stores - Pods
• people control access to
the data in their Pod
• standard, open, and
interoperable data
formats and protocols
Focus:
authentication &
authorization
KG 1 KG 2 KG 3
App A App B App C
Can my app B work on my KG2?
Example: How old are the students?
Query for all students, access age
Query fails during evaluation
let students = query { SELECT ?x WHERE {?x a Student. } }
for student in students do
printfn „%A“ (student.age)
bob
alice 𝑏1
Student
University
subClass
type
studiesAt
type
211... "Bob"
matrNr name
25 "Alice"
age name
Person
[ESOP17,ISWC19]
Example: How old are the students?
let students = query { SELECT ?x WHERE {?x a Student. } }
for student in students do
printfn „%A“ (student.age)
Should we use this relation on this signifier?
Depends on:
1. Conceptualization of data source
2. Querying of data source
3. Software code
bob
alice 𝑏1
Student
University
subClass
type
studiesAt
type
211... "Bob"
matrNr name
25 "Alice"
age name
Person
Closed-world conceptualization of classes and relations
SHACL – SHApes Constraint Language
• SHACL shapes are integrity constraints
• Namespaces omitted for brevity
:StudentShape a :NodeShape;
:targetClass :Student;
:class :Person;
:property [
:path :studiesAt;
:minCount 1;
:class :University;
].
:PersonShape a :NodeShape;
:targetClass :Person;
:property [
:path :name;
:minCount 1;
:datatype xsd:string;
].
Closed-world conceptualization of code (1)
Type checking discovers (potential) run-time errors
let students = query { SELECT ?x WHERE {?x a Student. } }
for student in students do
printfn „%A“ (student.age)
Set of all students (StudentShape)
One value of
StudentShape
set
Not allowed since
StudentShape ⊈ ≥𝟏age.⊤
when considering
all conceptually possible RDF graphs
Closed-world conceptualization of code (2)
• Access: matrNr
• No error during evaluation
• Unsafe: Rejected by type checking,
conceptualization not guaranteed
let students = query { SELECT ?x WHERE {?x a Student. } }
for student in students do
printfn „%A“ (student.matrNr)
bob
alice 𝑏1
Student
University
subClass
type
studiesAt
type
211... "Bob"
matrNr name
25 "Alice"
age name
Person
Closed-world conceptualization of code (3)
• Query for: matrNr
• Type safe access:
matrNr inferred to be given for all values of student
let students = query { SELECT ?x WHERE {?x matrNr ?y. } }
for student in students do
printfn „%A“ (student.matrNr)
bob
alice 𝑏1
Student
University
subClass
type
studiesAt
type
211... "Bob"
matrNr name
25 "Alice"
age name
Person
[ESOP17,ISWC19]
1. Use available SHACL constraints
2. Infer additional SHACL constraints from queries
3. Type check using inference
Determine type safety
let students = query { SELECT ?x WHERE {?x a Student. } }
for student in students do
printfn „%A“ (student.name)
Query shape(2) including StudentShape (1)
One value of
StudentShape
set
StudentShape ⊆ PersonShape and
PersonShape ⊆ ≥1name. ⊤ in all possible graphs
Inference (3)
[ESOP17,ISWC19]
KG 1 KG 2 KG 3
App A App B App C
Scenario: Can my app B work on my view of KG1?
32
Shapes to Shapes
KG 1 KG 2
App B
Input Shape
Sin = { :Person ⊑ :Agent
}
Input query defining view
q = CONSTRUCT {
?x a :Person .
?y a :Agent
} WHERE {
?x a :Person .
?y a :Agent
“Every Person
is an Agent” Output Shapes
“Which data can App B expect?”
s2s(Sin, q) → Sout
view
[Seifer2023]
Tracing Query Concepts (and Relations)
Sin = { :Person1 ⊑
:Agent }
q = CONSTRUCT {
?x a :Person3 .
?y a :Agent
} WHERE {
?x a :Person2 .
?y a :Agent
}
Sout = { :Person3 ⊑
:Agent }
Are concepts
:Person1
:Person2
:Person3
the same?
33
Yes!
[Seifer2023]
Tracing Query Concepts (and Relations)
Sin = { :Person1 ⊑ :Agent
}
q = CONSTRUCT {
?x a :Person3 .
?y a :Agent
} WHERE {
?x a :Person2 .
?x a :Teacher .
?y a :Agent
}
Sout = { :Person3 ⊑ :Agent
}
Are concepts
:Person1
:Person2
:Person3
still the same?
34
NO!
[Seifer2023]
Hard problem even for restricted
query and constraint languages
KG problems occur at ontological and at fact level.
Knowledge Graph technologies lack crucial capabilities
for guaranteeing results.
35
Observation 2
4 Knowing More
Deduction
• Ontological reasoning: description logics/OWL,
EL++, DL-lite
• Rule reasoning
Induction
• Rule learning and reasoning: AnyBurl, AMIE
• Knowledge Graph factorizations and embeddings:
Rescal, TransE
Similarity reasoning
• Similarities of entities, attributes, relations, ….
• Analogical reasoning
Knowing More than What is Stated in a Knowledge Graph
These
paradigms
overlap
• represent entities and relation names: 𝒉, 𝒓, 𝒕 ∈ ℝ𝑘
• embed triples (𝒉, 𝒓, 𝒕) ∈ ℝ𝑘 × ℝ𝑘 × ℝ𝑘 such that 𝒉 + 𝒓 ≈ 𝒕
• minimize error 𝒉 + 𝒓 − 𝒕
• regularize to avoid
trivial solutions
• Design modifications
geometric spaces, geometric operators, loss, regularizers…
38
TransE (Bordes et al 2013)
𝒆𝟏
𝒆𝟐
𝒆𝟑
𝒆𝟒
𝒓𝟏
𝒓𝟏
𝒓𝟐
𝒓𝟐
39
Finding and Exploiting Patterns of Similarity & Analogy
Stuttgart
Area
worksFor
locatedIn
Koblenz
Area
Wolv.
Area
Steffen
Frank
Ingo
birthdate
livesIn
prediction impossible prediction possible
Correct [2013]:
“TransE significantly outperforms state-of-the-art methods in link
prediction on two knowledge bases.”
Misleading:
“Our work focuses on modeling multi-relational data from KBs
(Wordnet [9] and Freebase [1] in this paper), with the goal of
providing an efficient tool to complete them by automatically
adding new facts, without requiring extra knowledge.”
A. Bordes et al. [TransE 2013]
Knowing More than What is Stated in a Knowledge Graph
Geometric Reasoning with EL Ontology A-Box
Concept assertion 𝐶(𝑎)
𝑎
𝐶
Geometric membership
[ISWC2022]
42
Geometric Reasoning with EL Ontology T-Box
Box affine
transformation
Box entailment Box intersection
Box disjointedness
[ISWC2022]
Geometric Reasoning with EL Ontology A-Box
4
3
Concept assertion 𝐶(𝑎)
𝑎
𝐶
r(𝑎, 𝑏)
𝑇𝑟
𝑏
𝑎
Role assertion
Geometric membership
Affine transformation
between two points
[ISWC2022]
44
Geometric Reasoning with Fact Attributions in ShrinkE
• Modeling primal triple as a spatial spanning (from a point to a box)
• Modeling qualifiers as a spatial (monotonically) shrinking of the box
• Qualifier implication and exclusion are geometrically modeled as
box containment and disjointedness
[ACL2023]
Check out https://kg-beyond-triple.github.io/
45
Geometric Reasoning with Fact Attributions in ShrinkE
[ACL2023]
• Box embedding
• Box shrinking is a box-to-box transform that monotonically shrinks the size
• WD50k: excerpt from Wikidata
• JF17K: excerpt from Freebase
• WikiPeople: excerpt from Wikidata
• FB15k-237: excerpt from Freebase
• …
Datasets for evaluating knowledge graph embeddings
Many datasets, but all biased in the same direction
02.11.2020
PhD thesis in preparation by Fabian Sasse, KIT 47
Selecting manufacturing measurement technology
in immature production processes
48
Ontological Case-based Reasoning using
Knowledge Graph Embeddings
PhD thesis in preparation by Fabian Sasse, KIT
Knowledge Graph embedding techniques
do not complete knowledge graphs,
they perform similarity and analogical reasoning.
Evaluations of Knowledge Graph embedding methods
remain biased towards encyclopedic knowledge.
49
Observation 3
5 Large Language
Models as
Knowledge Bases
51
ChatGPT on Frequently Observed Facts
Wikidata on Frequently Observed Facts
52
ChatGPT on Point Facts
Wikidata on Point Facts
2023-10-24
2023-10-22
53
One highly ranked result of Google search
Statistically frequent knowledge
• Commonsense knowledge:
• “cows eat grass”
• “apples fall towards earth if
unsupported”
• Commonsense expert
knowledge
• “halting problem is undecidable”
• “3SAT is NP-complete”
“Point knowledge”
• Steffen Staab is a professor
at University of Stuttgart
54
Knowledge in text
• Smoothing a data set: create an approximating function that
preserves patterns in the data, while leaving out noise or fine-
scale structures. [Shortened from Wikipedia]
• Laplacian smoothing for Naïve Bayes:
argmax𝑐 𝑃 𝑐 𝑥1, … , 𝑥𝑛 ≈ argmax𝑐𝑃 𝑐 𝑃 𝑥1 𝑐 ⋯ 𝑃 𝑥𝑛 𝑐
• Smoothing for language models [ACL14]
𝑃 𝑤𝑛 𝑤𝑛−𝑘 ⋯ 𝑤𝑛−1
must not be 0 for unobserved 𝑤𝑛−𝑘 ⋯ 𝑤𝑛−1 𝑤𝑛
55
Language models smoothen probability distributions
must not be 0
• What other terms could appear in a masked position?
• High “temperature” → diversity of answers
• Varying answers for “Write a poem about <your name>”
56
Smoothing is the core task of Large Language Models
57
Sampling diverse decisions towards preferred answers
5 different answers:
[Potyka23]
Language models are not fact repositories
but they are good representing commonly occurring facts.
58
Observation 4
6 Large Language
Models as
AI Assistants
60
Integrating Knowledge Graph Embeddings and
Pre-trained Language Models in Hypercomplex Spaces
[ISWC2023]
ex:AstonVilla ex:endedWinlessStreakAgainst
ex:WestHamUnited ;
ex:hasConsecutiveHomeVictories 11 ;
ex:hasMatch [
ex:hasScorer ex:DouglasLuiz,
ex:hasScorer ex:OllieWatkins,
ex:hasScorer ex:LeonBailey
] .
ex:DouglasLuiz a foaf:Person ;
foaf:name "Douglas Luiz" ;
ex:scoresFor "sixth league game running" ;
ex:scoresPenalty true ;
ex:doubledTally true .
ex:OllieWatkins a foaf:Person ;
foaf:name "Ollie Watkins" ;
ex:scoredForEngland true ;
ex:pulledShotWide true .
ex:WestHamUnited a ex:FootballClub .
ex:JarrodBowen a foaf:Person ;
foaf:name "Jarrod Bowen" ;
ex:deflectedShot true .
ex:JohnMcGinn a foaf:Person ;
foaf:name "John McGinn" ;
ex:providesAssist true .
ex:KurtZouma a foaf:Person ;
foaf:name "Kurt Zouma" ;
ex:disrupted true .
ex:MichailAntonio a foaf:Person ;
foaf:name "Michail Antonio" ;
ex:shotOnTarget true .
ex:EmiMartinez a foaf:Person ;
foaf:name "Emi Martinez" ;
ex:makesSmartStop true .
ex:LucasPaqueta a foaf:Person ;
61
Knowledge engineering by LLM translation
@prefix vfb: <http://example.com/soccerclub#>.
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>.
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>.
@prefix xsd: <http://www.w3.org/2001/XMLSchema#>.
vfb:VfB rdf:type vfb:SoccerClub; vfb:hasName "VfB"; vfb:hasNickname "Brustring".
vfb:SechsterErfolgInSerie rdf:type vfb:MatchResult; vfb:againstTeam vfb:UnionBerlin; vfb:withScore
"3:0”.
vfb:UnionBerlin rdf:type vfb:SoccerClub; vfb:hasName "1. FC Union Berlin".
vfb:MaxiMittelstaedt rdf:type vfb:Player; vfb:hasName "Maxi Mittelstädt".
vfb:DanAxelZagadou rdf:type vfb:Player; vfb:hasName "Dan-Axel Zagadou". vfb:PascalStenzel rdf:type
vfb:Player; vfb:hasName "Pascal Stenzel". vfb:HirokiIto rdf:type vfb:Player; vfb:hasName "Hiroki Ito".
vfb:SerhouGuirassy rdf:type vfb:Player; vfb:hasName "Serhou Guirassy"; vfb:hasGoals "1";
vfb:hasAssists "0". vfb:DenizUndav rdf:type vfb:Player; vfb:hasName "Deniz Undav"; vfb:hasGoals "1";
62
Knowledge engineering by LLM translation
63
Few shot in context learning on KB question answering
Tianle Li, Xueguang Ma, Alex Zhuang, Yu Gu, Yu Su,
and Wenhu Chen. 2023. Few-shot In-context Learning
on Knowledge Base Question Answering. In ACL-2023
64
Integration of knowledge graphs
by
language model
[SIGIR23]
Language models may be our translators and interfaces for
assisting the entering and retrieval of facts.
65
Observation 5
7 Conclusion
Knowing for Sure
• Research required for
dealing with federated,
overlapping KGs with
multiple authorities
Knowing More
• Know what you get and
evaluate not only with
encyclopedic KGs
LLMs as knowledge bases
• Commonsense knowledge
• Frequently observed
knowledge
LLMs as AI assistants
• entering and retrieving
“point knowledge”
Do not (always) go with the flow
Thank you!
E-Mail
www.
Universität Stuttgart
KI – Institute for Artificial Intelligence
Universitätsstraße 32, 70569 Stuttgart
Steffen Staab
ki.uni-stuttgart.de
Analytic Computing, KI
Steffen.staab@ki.uni-stuttgart.de
Many thanks go to my
PhD students, PostDocs and
collaborators who made the work
possible portrayed in this talk
check out references!
I hire
PostDoc & PhD student
for circular factory project!
1. [Potyka23] Nico Potyka, Yuqicheng Zhu, Evgeny Kharlamov and Steffen Staab.
Uncertainty-aware Knowledge Extraction from Large Language Models using
Social Choice Theory. TechReport.
2. [ISWC2022] B. Xiong, N. Potyka, T.-K. Tran, M. Nayyeri, S. Staab. For “Faithful
Embeddings for EL++ Knowledge Bases”. In: 21st International Semantic Web
Conference (ISWC2022)
3. [SIGIR23] J. Lu, J. Shen, B. Xiong, W. Ma, S. Staab, C. Yang. HiPrompt: Few-
Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting. In:
Proceedings of ACM SIGIR-2023, Taipei, Taiwan, July 23-27, 2023.
4. [ISWC2023] M. Nayyeri, Z. Wang, M. M. Akter, M. Mohtashim, Md R. Al Hasan
Rony, J. Lehmann, S. Staab. Integrating Knowledge Graph Embeddings and Pre-
trained Language Models in Hypercomplex Spaces. In: 22nd Int. Semantic Web
Conference (ISWC2023), Athens, GR, November 6-10, 2023.
5. [TransE 2013] Bordes, Antoine, et al. "Translating embeddings for modeling
multi-relational data." Advances in neural information processing systems 26
(2013).
References related to Knowing More
1. [ISWC19] M. Leinberger, P. Seifer, C. Schon, R. Lämmel, S. Staab. Type Checking Program Code using SHACL. In: Proc.
of Int. Semantic Web Conference (ISWC-2019). Auckland, New Zealand, October 2019.
2. [Seifer2023] Philipp Seifer, Daniel Hernández, Ralf Lämmel, Steffen Staab. From Shapes to Shapes: Inferring SHACL
Shapes for Results of SPARQL CONSTRUCT Queries. TechReport.
3. [ESOP17] M. Leinberger, R. Lämmel, S. Staab. The essence of functional programming on semantic data. In 26th
European Symposium on Programming (ESOP 2017), Uppsala, SE, 22 - 29 Apr 2017, pp. 750-776.
4. [CAAD Futures 2023] D. Elshani, D. Hernandez, A. Lombardi, L. Siriwardena, T. Schwinn, A. Fisher, S. Staab, A. Menges,
T. Wortmann. Building Information Validation and Reasoning Using Semantic Web Technologies. In: Computer-Aided
Architectural Design. CAAD Futures 2023. Springer, Cham, 2023.
5. [KR2020] T. Rienstra, C. Schon, S. Staab. Concept Contraction in the Description Logic EL. In: Principles of Knowledge
Representation and Reasoning: Proceedings of the Seventeenth International Conference, KR 2020, pp. 723-732.
6. [EKAW18] C. Schon, S. Staab, P. Kügler, P. Kestel, B. Schleich, S. Wartzack. Metaproperty-guided Deletion from the
Instance-Level of a Knowledge Base. In: Proc. of EKAW 2018, 21st International Conference on Knowledge Engineering
and Knowledge Management, November 12-16, 2018, Nancy, France, Springer 2018.
7. [ESWC2013] S. Scheglmann, S. Staab, M. Thimm, G. Gröner. Locking for Concurrent Transactions on Ontologies. In: 10th
Extended Semantic Web Conference (ESWC2013), Montpellier, France, May 26-30, 2013.
8. [WWW08] S. Schenk, S. Staab. Networked Graphs: A Declarative Mechanism for SPARQL Rules, SPARQL Views and RDF
Data Integration on the Web. In: Proc. of WWW-2008, 17th Int. World Wide Web Conference, Bejing, China, April 21-25,
2008, pp. 585-594.
References related to Knowing for Sure
[ACL14] R. Pickhardt, T. Gottron, M. Körner, P. G. Wagner, T. Speicher, S. Staab. A Generalized Language Model as the
Combination of Skipped n-grams and Modified Kneser Ney Smoothing. In: Proc. of ACL-2014 - The 52nd Annual Meeting of the
Association for Computational Linguistics. Baltimore, June 22-27, 2014.
02.11.2020
Steffen Staab, Universität Stuttgart, @ststaab, https://www.ipvs.uni-stuttgart.de/departments/ac/ 71
Others

More Related Content

What's hot

ICSE23 Keynote: Software Engineering as the Linchpin of Responsible AI
ICSE23 Keynote: Software Engineering as the Linchpin of Responsible AIICSE23 Keynote: Software Engineering as the Linchpin of Responsible AI
ICSE23 Keynote: Software Engineering as the Linchpin of Responsible AILiming Zhu
 
Ethics in the use of Data & AI
Ethics in the use of Data & AI Ethics in the use of Data & AI
Ethics in the use of Data & AI Kalilur Rahman
 
Knowledge Graph Introduction
Knowledge Graph IntroductionKnowledge Graph Introduction
Knowledge Graph IntroductionSören Auer
 
Neo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph Algorithms
Neo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph AlgorithmsNeo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph Algorithms
Neo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph AlgorithmsNeo4j
 
Accelerating Path to Production for Generative AI-powered Applications
Accelerating Path to Production for Generative AI-powered ApplicationsAccelerating Path to Production for Generative AI-powered Applications
Accelerating Path to Production for Generative AI-powered ApplicationsHostedbyConfluent
 
Machine Learning & Embeddings for Large Knowledge Graphs
Machine Learning & Embeddings  for Large Knowledge GraphsMachine Learning & Embeddings  for Large Knowledge Graphs
Machine Learning & Embeddings for Large Knowledge GraphsHeiko Paulheim
 
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Krishnaram Kenthapadi
 
The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"Frank van Harmelen
 
Intro to nlp
Intro to nlpIntro to nlp
Intro to nlpankit_ppt
 
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...Daniel Zivkovic
 
Large Language Models, Data & APIs - Integrating Generative AI Power into you...
Large Language Models, Data & APIs - Integrating Generative AI Power into you...Large Language Models, Data & APIs - Integrating Generative AI Power into you...
Large Language Models, Data & APIs - Integrating Generative AI Power into you...NETUserGroupBern
 
How ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyHow ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyPekka Abrahamsson / Tampere University
 
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1DianaGray10
 
Introduction to Knowledge Graphs
Introduction to Knowledge GraphsIntroduction to Knowledge Graphs
Introduction to Knowledge Graphsmukuljoshi
 
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...David Talby
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMsSylvainGugger
 

What's hot (20)

ICSE23 Keynote: Software Engineering as the Linchpin of Responsible AI
ICSE23 Keynote: Software Engineering as the Linchpin of Responsible AIICSE23 Keynote: Software Engineering as the Linchpin of Responsible AI
ICSE23 Keynote: Software Engineering as the Linchpin of Responsible AI
 
Ethics in the use of Data & AI
Ethics in the use of Data & AI Ethics in the use of Data & AI
Ethics in the use of Data & AI
 
Knowledge Graph Introduction
Knowledge Graph IntroductionKnowledge Graph Introduction
Knowledge Graph Introduction
 
Neo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph Algorithms
Neo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph AlgorithmsNeo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph Algorithms
Neo4j Graph Data Science Training - June 9 & 10 - Slides #6 Graph Algorithms
 
Accelerating Path to Production for Generative AI-powered Applications
Accelerating Path to Production for Generative AI-powered ApplicationsAccelerating Path to Production for Generative AI-powered Applications
Accelerating Path to Production for Generative AI-powered Applications
 
Machine Learning & Embeddings for Large Knowledge Graphs
Machine Learning & Embeddings  for Large Knowledge GraphsMachine Learning & Embeddings  for Large Knowledge Graphs
Machine Learning & Embeddings for Large Knowledge Graphs
 
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
 
The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"The K in "neuro-symbolic" stands for "knowledge"
The K in "neuro-symbolic" stands for "knowledge"
 
LLMs Bootcamp
LLMs BootcampLLMs Bootcamp
LLMs Bootcamp
 
Intro to nlp
Intro to nlpIntro to nlp
Intro to nlp
 
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
 
Large Language Models, Data & APIs - Integrating Generative AI Power into you...
Large Language Models, Data & APIs - Integrating Generative AI Power into you...Large Language Models, Data & APIs - Integrating Generative AI Power into you...
Large Language Models, Data & APIs - Integrating Generative AI Power into you...
 
How ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundlyHow ChatGPT and AI-assisted coding changes software engineering profoundly
How ChatGPT and AI-assisted coding changes software engineering profoundly
 
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
 
Introduction to Knowledge Graphs
Introduction to Knowledge GraphsIntroduction to Knowledge Graphs
Introduction to Knowledge Graphs
 
Responsible AI
Responsible AIResponsible AI
Responsible AI
 
Bias in AI
Bias in AIBias in AI
Bias in AI
 
Word embedding
Word embedding Word embedding
Word embedding
 
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMs
 

Similar to Knowledge graphs for knowing more and knowing for sure

Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Steffen Staab
 
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Sri Ambati
 
Dad (Data Analysis And Design)
Dad (Data Analysis And Design)Dad (Data Analysis And Design)
Dad (Data Analysis And Design)Jill Lyons
 
Data-centric AI and the convergence of data and model engineering: opportunit...
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...Paolo Missier
 
DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...
DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...
DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...DataMind-slides
 
INF 103(ASH) Possible Is Everything/newtonhelp.com
INF 103(ASH) Possible Is Everything/newtonhelp.comINF 103(ASH) Possible Is Everything/newtonhelp.com
INF 103(ASH) Possible Is Everything/newtonhelp.comlechenau71
 
INF 103(ASH) Learn/newtonhelp.com
INF 103(ASH) Learn/newtonhelp.comINF 103(ASH) Learn/newtonhelp.com
INF 103(ASH) Learn/newtonhelp.comlechenau48
 
2014-10-10-SBC361-Reproducible research
2014-10-10-SBC361-Reproducible research2014-10-10-SBC361-Reproducible research
2014-10-10-SBC361-Reproducible researchYannick Wurm
 
The Semantic Knowledge Graph
The Semantic Knowledge GraphThe Semantic Knowledge Graph
The Semantic Knowledge GraphTrey Grainger
 
Unit_4- Principles of AI explaining the importants of AI
Unit_4- Principles of AI explaining the importants of AIUnit_4- Principles of AI explaining the importants of AI
Unit_4- Principles of AI explaining the importants of AIVijayAECE1
 
C++ plus data structures, 3rd edition (2003)
C++ plus data structures, 3rd edition (2003)C++ plus data structures, 3rd edition (2003)
C++ plus data structures, 3rd edition (2003)SHC
 
Lec 1 integrating data science and data analytics in various research thrust
Lec 1 integrating data science and data analytics in various research thrustLec 1 integrating data science and data analytics in various research thrust
Lec 1 integrating data science and data analytics in various research thrustMenchita Falcutila Dumlao
 
Predictive Model and Record Description with Segmented Sensitivity Analysis (...
Predictive Model and Record Description with Segmented Sensitivity Analysis (...Predictive Model and Record Description with Segmented Sensitivity Analysis (...
Predictive Model and Record Description with Segmented Sensitivity Analysis (...Greg Makowski
 
Scientific Knowledge Graphs: an Overview
Scientific Knowledge Graphs: an OverviewScientific Knowledge Graphs: an Overview
Scientific Knowledge Graphs: an OverviewAngelo Salatino
 
On the Impact of sameAs on Schema Matching
On the Impact of sameAs on Schema MatchingOn the Impact of sameAs on Schema Matching
On the Impact of sameAs on Schema MatchingJoe Raad
 
Driverless AI Hands-on Focused on Machine Learning Interpretability - H2O.ai
Driverless AI Hands-on Focused on Machine Learning Interpretability - H2O.aiDriverless AI Hands-on Focused on Machine Learning Interpretability - H2O.ai
Driverless AI Hands-on Focused on Machine Learning Interpretability - H2O.aiSri Ambati
 
Multi-Model Data Query Languages and Processing Paradigms
Multi-Model Data Query Languages and Processing ParadigmsMulti-Model Data Query Languages and Processing Paradigms
Multi-Model Data Query Languages and Processing ParadigmsJiaheng Lu
 
Introduction to oop
Introduction to oop Introduction to oop
Introduction to oop Kumar
 

Similar to Knowledge graphs for knowing more and knowing for sure (20)

Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
 
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
 
Dad (Data Analysis And Design)
Dad (Data Analysis And Design)Dad (Data Analysis And Design)
Dad (Data Analysis And Design)
 
Data-centric AI and the convergence of data and model engineering: opportunit...
Data-centric AI and the convergence of data and model engineering:opportunit...Data-centric AI and the convergence of data and model engineering:opportunit...
Data-centric AI and the convergence of data and model engineering: opportunit...
 
DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...
DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...
DataMind: An e-learning platform for Data Analysis based on R. RBelgium meetu...
 
INF 103(ASH) Possible Is Everything/newtonhelp.com
INF 103(ASH) Possible Is Everything/newtonhelp.comINF 103(ASH) Possible Is Everything/newtonhelp.com
INF 103(ASH) Possible Is Everything/newtonhelp.com
 
INF 103(ASH) Learn/newtonhelp.com
INF 103(ASH) Learn/newtonhelp.comINF 103(ASH) Learn/newtonhelp.com
INF 103(ASH) Learn/newtonhelp.com
 
2014-10-10-SBC361-Reproducible research
2014-10-10-SBC361-Reproducible research2014-10-10-SBC361-Reproducible research
2014-10-10-SBC361-Reproducible research
 
The Semantic Knowledge Graph
The Semantic Knowledge GraphThe Semantic Knowledge Graph
The Semantic Knowledge Graph
 
Unit_4- Principles of AI explaining the importants of AI
Unit_4- Principles of AI explaining the importants of AIUnit_4- Principles of AI explaining the importants of AI
Unit_4- Principles of AI explaining the importants of AI
 
C++ plus data structures, 3rd edition (2003)
C++ plus data structures, 3rd edition (2003)C++ plus data structures, 3rd edition (2003)
C++ plus data structures, 3rd edition (2003)
 
Lec 1 integrating data science and data analytics in various research thrust
Lec 1 integrating data science and data analytics in various research thrustLec 1 integrating data science and data analytics in various research thrust
Lec 1 integrating data science and data analytics in various research thrust
 
Predictive Model and Record Description with Segmented Sensitivity Analysis (...
Predictive Model and Record Description with Segmented Sensitivity Analysis (...Predictive Model and Record Description with Segmented Sensitivity Analysis (...
Predictive Model and Record Description with Segmented Sensitivity Analysis (...
 
Scientific Knowledge Graphs: an Overview
Scientific Knowledge Graphs: an OverviewScientific Knowledge Graphs: an Overview
Scientific Knowledge Graphs: an Overview
 
On the Impact of sameAs on Schema Matching
On the Impact of sameAs on Schema MatchingOn the Impact of sameAs on Schema Matching
On the Impact of sameAs on Schema Matching
 
Nlp workshop-share
Nlp workshop-shareNlp workshop-share
Nlp workshop-share
 
Driverless AI Hands-on Focused on Machine Learning Interpretability - H2O.ai
Driverless AI Hands-on Focused on Machine Learning Interpretability - H2O.aiDriverless AI Hands-on Focused on Machine Learning Interpretability - H2O.ai
Driverless AI Hands-on Focused on Machine Learning Interpretability - H2O.ai
 
Multi-Model Data Query Languages and Processing Paradigms
Multi-Model Data Query Languages and Processing ParadigmsMulti-Model Data Query Languages and Processing Paradigms
Multi-Model Data Query Languages and Processing Paradigms
 
Data-X-Sparse-v2
Data-X-Sparse-v2Data-X-Sparse-v2
Data-X-Sparse-v2
 
Introduction to oop
Introduction to oop Introduction to oop
Introduction to oop
 

More from Steffen Staab

Symbolic Background Knowledge for Machine Learning
Symbolic Background Knowledge for Machine LearningSymbolic Background Knowledge for Machine Learning
Symbolic Background Knowledge for Machine LearningSteffen Staab
 
Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...
Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...
Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...Steffen Staab
 
Web Futures: Inclusive, Intelligent, Sustainable
Web Futures: Inclusive, Intelligent, SustainableWeb Futures: Inclusive, Intelligent, Sustainable
Web Futures: Inclusive, Intelligent, SustainableSteffen Staab
 
Concepts in Application Context ( How we may think conceptually )
Concepts in Application Context ( How we may think conceptually )Concepts in Application Context ( How we may think conceptually )
Concepts in Application Context ( How we may think conceptually )Steffen Staab
 
Storing and Querying Semantic Data in the Cloud
Storing and Querying Semantic Data in the CloudStoring and Querying Semantic Data in the Cloud
Storing and Querying Semantic Data in the CloudSteffen Staab
 
Ontologien und Semantic Web - Impulsvortrag Terminologietag
Ontologien und Semantic Web - Impulsvortrag TerminologietagOntologien und Semantic Web - Impulsvortrag Terminologietag
Ontologien und Semantic Web - Impulsvortrag TerminologietagSteffen Staab
 
Opinion Formation and Spreading
Opinion Formation and SpreadingOpinion Formation and Spreading
Opinion Formation and SpreadingSteffen Staab
 
10 Jahre Web Science
10 Jahre Web Science10 Jahre Web Science
10 Jahre Web ScienceSteffen Staab
 
(Semi-)Automatic analysis of online contents
(Semi-)Automatic analysis of online contents(Semi-)Automatic analysis of online contents
(Semi-)Automatic analysis of online contentsSteffen Staab
 
Programming with Semantic Broad Data
Programming with Semantic Broad DataProgramming with Semantic Broad Data
Programming with Semantic Broad DataSteffen Staab
 
Text Mining using LDA with Context
Text Mining using LDA with ContextText Mining using LDA with Context
Text Mining using LDA with ContextSteffen Staab
 
Wwsss intro2016-final
Wwsss intro2016-finalWwsss intro2016-final
Wwsss intro2016-finalSteffen Staab
 
10 Years Web Science
10 Years Web Science10 Years Web Science
10 Years Web ScienceSteffen Staab
 
Semantic Web Technologies: Principles and Practices
Semantic Web Technologies: Principles and PracticesSemantic Web Technologies: Principles and Practices
Semantic Web Technologies: Principles and PracticesSteffen Staab
 
Closing Session ISWC 2015
Closing Session ISWC 2015Closing Session ISWC 2015
Closing Session ISWC 2015Steffen Staab
 
ISWC2015 Opening Session
ISWC2015 Opening SessionISWC2015 Opening Session
ISWC2015 Opening SessionSteffen Staab
 
Bias in the Social Web
Bias in the Social WebBias in the Social Web
Bias in the Social WebSteffen Staab
 

More from Steffen Staab (20)

Symbolic Background Knowledge for Machine Learning
Symbolic Background Knowledge for Machine LearningSymbolic Background Knowledge for Machine Learning
Symbolic Background Knowledge for Machine Learning
 
Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...
Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...
Soziale Netzwerke und Medien: Multi-disziplinäre Ansätze für ein multi-dimens...
 
Web Futures: Inclusive, Intelligent, Sustainable
Web Futures: Inclusive, Intelligent, SustainableWeb Futures: Inclusive, Intelligent, Sustainable
Web Futures: Inclusive, Intelligent, Sustainable
 
Eyeing the Web
Eyeing the WebEyeing the Web
Eyeing the Web
 
Concepts in Application Context ( How we may think conceptually )
Concepts in Application Context ( How we may think conceptually )Concepts in Application Context ( How we may think conceptually )
Concepts in Application Context ( How we may think conceptually )
 
Storing and Querying Semantic Data in the Cloud
Storing and Querying Semantic Data in the CloudStoring and Querying Semantic Data in the Cloud
Storing and Querying Semantic Data in the Cloud
 
Semantics reloaded
Semantics reloadedSemantics reloaded
Semantics reloaded
 
Ontologien und Semantic Web - Impulsvortrag Terminologietag
Ontologien und Semantic Web - Impulsvortrag TerminologietagOntologien und Semantic Web - Impulsvortrag Terminologietag
Ontologien und Semantic Web - Impulsvortrag Terminologietag
 
Opinion Formation and Spreading
Opinion Formation and SpreadingOpinion Formation and Spreading
Opinion Formation and Spreading
 
The Web We Want
The Web We WantThe Web We Want
The Web We Want
 
10 Jahre Web Science
10 Jahre Web Science10 Jahre Web Science
10 Jahre Web Science
 
(Semi-)Automatic analysis of online contents
(Semi-)Automatic analysis of online contents(Semi-)Automatic analysis of online contents
(Semi-)Automatic analysis of online contents
 
Programming with Semantic Broad Data
Programming with Semantic Broad DataProgramming with Semantic Broad Data
Programming with Semantic Broad Data
 
Text Mining using LDA with Context
Text Mining using LDA with ContextText Mining using LDA with Context
Text Mining using LDA with Context
 
Wwsss intro2016-final
Wwsss intro2016-finalWwsss intro2016-final
Wwsss intro2016-final
 
10 Years Web Science
10 Years Web Science10 Years Web Science
10 Years Web Science
 
Semantic Web Technologies: Principles and Practices
Semantic Web Technologies: Principles and PracticesSemantic Web Technologies: Principles and Practices
Semantic Web Technologies: Principles and Practices
 
Closing Session ISWC 2015
Closing Session ISWC 2015Closing Session ISWC 2015
Closing Session ISWC 2015
 
ISWC2015 Opening Session
ISWC2015 Opening SessionISWC2015 Opening Session
ISWC2015 Opening Session
 
Bias in the Social Web
Bias in the Social WebBias in the Social Web
Bias in the Social Web
 

Recently uploaded

Tales from a Passkey Provider Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider  Progress from Awareness to Implementation.pptxTales from a Passkey Provider  Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider Progress from Awareness to Implementation.pptxFIDO Alliance
 
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptxHarnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptxFIDO Alliance
 
How we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdfHow we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdfSrushith Repakula
 
AI mind or machine power point presentation
AI mind or machine power point presentationAI mind or machine power point presentation
AI mind or machine power point presentationyogeshlabana357357
 
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...Skynet Technologies
 
Google I/O Extended 2024 Warsaw
Google I/O Extended 2024 WarsawGoogle I/O Extended 2024 Warsaw
Google I/O Extended 2024 WarsawGDSC PJATK
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfFIDO Alliance
 
2024 May Patch Tuesday
2024 May Patch Tuesday2024 May Patch Tuesday
2024 May Patch TuesdayIvanti
 
Using IESVE for Room Loads Analysis - UK & Ireland
Using IESVE for Room Loads Analysis - UK & IrelandUsing IESVE for Room Loads Analysis - UK & Ireland
Using IESVE for Room Loads Analysis - UK & IrelandIES VE
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data SciencePaolo Missier
 
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...ScyllaDB
 
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdfMuhammad Subhan
 
WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024Lorenzo Miniero
 
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...FIDO Alliance
 
Vector Search @ sw2con for slideshare.pptx
Vector Search @ sw2con for slideshare.pptxVector Search @ sw2con for slideshare.pptx
Vector Search @ sw2con for slideshare.pptxjbellis
 
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdfLinux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdfFIDO Alliance
 
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsContinuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsLeah Henrickson
 
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...FIDO Alliance
 
Top 10 CodeIgniter Development Companies
Top 10 CodeIgniter Development CompaniesTop 10 CodeIgniter Development Companies
Top 10 CodeIgniter Development CompaniesTopCSSGallery
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe中 央社
 

Recently uploaded (20)

Tales from a Passkey Provider Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider  Progress from Awareness to Implementation.pptxTales from a Passkey Provider  Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider Progress from Awareness to Implementation.pptx
 
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptxHarnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
 
How we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdfHow we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdf
 
AI mind or machine power point presentation
AI mind or machine power point presentationAI mind or machine power point presentation
AI mind or machine power point presentation
 
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
 
Google I/O Extended 2024 Warsaw
Google I/O Extended 2024 WarsawGoogle I/O Extended 2024 Warsaw
Google I/O Extended 2024 Warsaw
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
 
2024 May Patch Tuesday
2024 May Patch Tuesday2024 May Patch Tuesday
2024 May Patch Tuesday
 
Using IESVE for Room Loads Analysis - UK & Ireland
Using IESVE for Room Loads Analysis - UK & IrelandUsing IESVE for Room Loads Analysis - UK & Ireland
Using IESVE for Room Loads Analysis - UK & Ireland
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data Science
 
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
 
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
 
WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024
 
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
 
Vector Search @ sw2con for slideshare.pptx
Vector Search @ sw2con for slideshare.pptxVector Search @ sw2con for slideshare.pptx
Vector Search @ sw2con for slideshare.pptx
 
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdfLinux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
 
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsContinuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
 
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
 
Top 10 CodeIgniter Development Companies
Top 10 CodeIgniter Development CompaniesTop 10 CodeIgniter Development Companies
Top 10 CodeIgniter Development Companies
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 

Knowledge graphs for knowing more and knowing for sure

  • 1. KI – Institute for Artificial Intelligence Knowledge graphs for knowing more and knowing for sure Steffen Staab @ststaab https://www.ki.uni-stuttgart.de https://semanux.com https://southampton.ac.uk/research/institutes-centres/web-internet-science
  • 2. provides an international forum for presentation and discussion of research on information and knowledge management, as well as recent advances on data and knowledge bases. 2 Conference on Information and Knowledge Management Rather: Conference on Large Language Models? Let’s explore the role of knowledge bases/graphs!
  • 3. 1. What is a Knowledge Graph? 2. Some Applications of Knowledge Graphs 3. Knowledge Graphs for Knowing for Sure 4. Knowledge Graphs for Knowing More 5. Large Language Models as Knowledge Bases 6. Large Language Models as AI Assistants 3 Plan for my talk
  • 4. 1 What is a Knowledge Graph?
  • 5. What is a Knowledge Graph? A model for knowledge structures with 5 C22.0 Patient2342 treatedBy „liver tumor“ / „PhValue 7.5“ Concepts Entities Relations Labels / Values
  • 6. Queries • Scalability to billions of facts • Answering with • facts • predictions • recommendations 6 What does a knowledge graph do for us? What are the difficulties? Example from medical project: • Foundational Model of Anatomy: 75.000 concepts, 120.000 labels, > 2 Mio facts • Not even patient data yet!
  • 7. Queries Ontologies & Facts • How to develop and integrate ontologies? • How to provide facts? • Reasoning? • Learning? • Guarantees? 7 What does a knowledge graph do for us? What are the difficulties? Example from medical project: • Foundational Model of Anatomy • RadLex • ICD-10
  • 8. Queries Ontologies & Facts What can be represented? • Provenance • Uncertainty • Time • … 8 What does a knowledge graph do for us? What are the difficulties? Example from medical project: • Patient history • patient measurements
  • 9. 2 Some Applications of Knowledge Graphs
  • 10. 02.11.2020 Steffen Staab, Universität Stuttgart, @ststaab, https://www.ipvs.uni-stuttgart.de/departments/ac/ 10 Encyclopedic Knowledge Graph
  • 11. 02.11.2020 Steffen Staab, Universität Stuttgart, @ststaab, https://www.ipvs.uni-stuttgart.de/departments/ac/ 11 Wonderful ressource – but not representative
  • 12. 12 Application 1: Bosch Semantic Stack © Kalaycı, Elem Güzel, et al. "Semantic integration of Bosch manufacturing data using virtual knowledge graphs." ISWC 2020: 19th International Semantic Web Conference, Springer, 2020.
  • 13. Application 2: KG for Circular Factory Product Production Co- Design Knowledge Graph contains knowledge about design, production and product including plans, sensor measurements and intra-logistics
  • 14. 14 Application 3: Architecture, Engineering, Construction [CAAD Futures 2023] Collaboration with architects Happold, London
  • 15. https://pixabay.com/de/users/peggy_marco-1553824/ KG-S Simul structural engineering KG-A Design architectural design KG-C Constr construction customer requirements acoustic engineering electrical engineering ventilation fire containment plumbing …. many stakeholders many tools work in parallel, no waterfall mutual dependencies
  • 16. KG-A Design architectural design many stakeholders many tools work in parallel, no waterfall mutual dependencies code as agent https://vimeo.com/372594657
  • 17. • Updates and deletions with dependencies [EKAW18], also at the ontological level [KR2020] • Federation [WWW08] • Lacking views with deletions and updates • Transaction locking [ESWC2013] • Lacking recent standards (SHACL) and optimistic schemes • Uncertainties • Managing identities („does re-designed column preserve its identity?“) • ... 17 Applications Imply Wealth of Requirements rudimentary available research
  • 18. Encyclopedic KGs • Facts are reported often • Who is Douglas Adams? • What is the capital of France? • Head of distribution of world knowledge on the Web • Answers with high precision retrieval desired Engineering KGs • Point facts exist once • w3476 instOf AngleGrinder • faceGear4223 maxDeviation 0.3mm • Processes are important • Answers must be correct 18 Sliding scale of knowledge graph requirements Currently fashionable research “we build a system” under-researched
  • 19. A lot of research in Knowledge Graphs builds on the assumption that we want to query encyclopedias but we have many other requirements in industry. 19 Observation 1
  • 21. KG 1 KG 2 KG 3 App A App B App C Scenario in Architecture, Engineering, Construction (AEC)
  • 22. 22 SOLID Project https://solidproject.org/ • people store their data securely in decentralized data stores - Pods • people control access to the data in their Pod • standard, open, and interoperable data formats and protocols Focus: authentication & authorization
  • 23. KG 1 KG 2 KG 3 App A App B App C Can my app B work on my KG2?
  • 24. Example: How old are the students? Query for all students, access age Query fails during evaluation let students = query { SELECT ?x WHERE {?x a Student. } } for student in students do printfn „%A“ (student.age) bob alice 𝑏1 Student University subClass type studiesAt type 211... "Bob" matrNr name 25 "Alice" age name Person [ESOP17,ISWC19]
  • 25. Example: How old are the students? let students = query { SELECT ?x WHERE {?x a Student. } } for student in students do printfn „%A“ (student.age) Should we use this relation on this signifier? Depends on: 1. Conceptualization of data source 2. Querying of data source 3. Software code bob alice 𝑏1 Student University subClass type studiesAt type 211... "Bob" matrNr name 25 "Alice" age name Person
  • 26. Closed-world conceptualization of classes and relations SHACL – SHApes Constraint Language • SHACL shapes are integrity constraints • Namespaces omitted for brevity :StudentShape a :NodeShape; :targetClass :Student; :class :Person; :property [ :path :studiesAt; :minCount 1; :class :University; ]. :PersonShape a :NodeShape; :targetClass :Person; :property [ :path :name; :minCount 1; :datatype xsd:string; ].
  • 27. Closed-world conceptualization of code (1) Type checking discovers (potential) run-time errors let students = query { SELECT ?x WHERE {?x a Student. } } for student in students do printfn „%A“ (student.age) Set of all students (StudentShape) One value of StudentShape set Not allowed since StudentShape ⊈ ≥𝟏age.⊤ when considering all conceptually possible RDF graphs
  • 28. Closed-world conceptualization of code (2) • Access: matrNr • No error during evaluation • Unsafe: Rejected by type checking, conceptualization not guaranteed let students = query { SELECT ?x WHERE {?x a Student. } } for student in students do printfn „%A“ (student.matrNr) bob alice 𝑏1 Student University subClass type studiesAt type 211... "Bob" matrNr name 25 "Alice" age name Person
  • 29. Closed-world conceptualization of code (3) • Query for: matrNr • Type safe access: matrNr inferred to be given for all values of student let students = query { SELECT ?x WHERE {?x matrNr ?y. } } for student in students do printfn „%A“ (student.matrNr) bob alice 𝑏1 Student University subClass type studiesAt type 211... "Bob" matrNr name 25 "Alice" age name Person [ESOP17,ISWC19]
  • 30. 1. Use available SHACL constraints 2. Infer additional SHACL constraints from queries 3. Type check using inference Determine type safety let students = query { SELECT ?x WHERE {?x a Student. } } for student in students do printfn „%A“ (student.name) Query shape(2) including StudentShape (1) One value of StudentShape set StudentShape ⊆ PersonShape and PersonShape ⊆ ≥1name. ⊤ in all possible graphs Inference (3) [ESOP17,ISWC19]
  • 31. KG 1 KG 2 KG 3 App A App B App C Scenario: Can my app B work on my view of KG1?
  • 32. 32 Shapes to Shapes KG 1 KG 2 App B Input Shape Sin = { :Person ⊑ :Agent } Input query defining view q = CONSTRUCT { ?x a :Person . ?y a :Agent } WHERE { ?x a :Person . ?y a :Agent “Every Person is an Agent” Output Shapes “Which data can App B expect?” s2s(Sin, q) → Sout view [Seifer2023]
  • 33. Tracing Query Concepts (and Relations) Sin = { :Person1 ⊑ :Agent } q = CONSTRUCT { ?x a :Person3 . ?y a :Agent } WHERE { ?x a :Person2 . ?y a :Agent } Sout = { :Person3 ⊑ :Agent } Are concepts :Person1 :Person2 :Person3 the same? 33 Yes! [Seifer2023]
  • 34. Tracing Query Concepts (and Relations) Sin = { :Person1 ⊑ :Agent } q = CONSTRUCT { ?x a :Person3 . ?y a :Agent } WHERE { ?x a :Person2 . ?x a :Teacher . ?y a :Agent } Sout = { :Person3 ⊑ :Agent } Are concepts :Person1 :Person2 :Person3 still the same? 34 NO! [Seifer2023] Hard problem even for restricted query and constraint languages
  • 35. KG problems occur at ontological and at fact level. Knowledge Graph technologies lack crucial capabilities for guaranteeing results. 35 Observation 2
  • 37. Deduction • Ontological reasoning: description logics/OWL, EL++, DL-lite • Rule reasoning Induction • Rule learning and reasoning: AnyBurl, AMIE • Knowledge Graph factorizations and embeddings: Rescal, TransE Similarity reasoning • Similarities of entities, attributes, relations, …. • Analogical reasoning Knowing More than What is Stated in a Knowledge Graph These paradigms overlap
  • 38. • represent entities and relation names: 𝒉, 𝒓, 𝒕 ∈ ℝ𝑘 • embed triples (𝒉, 𝒓, 𝒕) ∈ ℝ𝑘 × ℝ𝑘 × ℝ𝑘 such that 𝒉 + 𝒓 ≈ 𝒕 • minimize error 𝒉 + 𝒓 − 𝒕 • regularize to avoid trivial solutions • Design modifications geometric spaces, geometric operators, loss, regularizers… 38 TransE (Bordes et al 2013) 𝒆𝟏 𝒆𝟐 𝒆𝟑 𝒆𝟒 𝒓𝟏 𝒓𝟏 𝒓𝟐 𝒓𝟐
  • 39. 39 Finding and Exploiting Patterns of Similarity & Analogy Stuttgart Area worksFor locatedIn Koblenz Area Wolv. Area Steffen Frank Ingo birthdate livesIn prediction impossible prediction possible
  • 40. Correct [2013]: “TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.” Misleading: “Our work focuses on modeling multi-relational data from KBs (Wordnet [9] and Freebase [1] in this paper), with the goal of providing an efficient tool to complete them by automatically adding new facts, without requiring extra knowledge.” A. Bordes et al. [TransE 2013] Knowing More than What is Stated in a Knowledge Graph
  • 41. Geometric Reasoning with EL Ontology A-Box Concept assertion 𝐶(𝑎) 𝑎 𝐶 Geometric membership [ISWC2022]
  • 42. 42 Geometric Reasoning with EL Ontology T-Box Box affine transformation Box entailment Box intersection Box disjointedness [ISWC2022]
  • 43. Geometric Reasoning with EL Ontology A-Box 4 3 Concept assertion 𝐶(𝑎) 𝑎 𝐶 r(𝑎, 𝑏) 𝑇𝑟 𝑏 𝑎 Role assertion Geometric membership Affine transformation between two points [ISWC2022]
  • 44. 44 Geometric Reasoning with Fact Attributions in ShrinkE • Modeling primal triple as a spatial spanning (from a point to a box) • Modeling qualifiers as a spatial (monotonically) shrinking of the box • Qualifier implication and exclusion are geometrically modeled as box containment and disjointedness [ACL2023] Check out https://kg-beyond-triple.github.io/
  • 45. 45 Geometric Reasoning with Fact Attributions in ShrinkE [ACL2023] • Box embedding • Box shrinking is a box-to-box transform that monotonically shrinks the size
  • 46. • WD50k: excerpt from Wikidata • JF17K: excerpt from Freebase • WikiPeople: excerpt from Wikidata • FB15k-237: excerpt from Freebase • … Datasets for evaluating knowledge graph embeddings Many datasets, but all biased in the same direction
  • 47. 02.11.2020 PhD thesis in preparation by Fabian Sasse, KIT 47 Selecting manufacturing measurement technology in immature production processes
  • 48. 48 Ontological Case-based Reasoning using Knowledge Graph Embeddings PhD thesis in preparation by Fabian Sasse, KIT
  • 49. Knowledge Graph embedding techniques do not complete knowledge graphs, they perform similarity and analogical reasoning. Evaluations of Knowledge Graph embedding methods remain biased towards encyclopedic knowledge. 49 Observation 3
  • 50. 5 Large Language Models as Knowledge Bases
  • 51. 51 ChatGPT on Frequently Observed Facts Wikidata on Frequently Observed Facts
  • 52. 52 ChatGPT on Point Facts Wikidata on Point Facts 2023-10-24 2023-10-22
  • 53. 53 One highly ranked result of Google search
  • 54. Statistically frequent knowledge • Commonsense knowledge: • “cows eat grass” • “apples fall towards earth if unsupported” • Commonsense expert knowledge • “halting problem is undecidable” • “3SAT is NP-complete” “Point knowledge” • Steffen Staab is a professor at University of Stuttgart 54 Knowledge in text
  • 55. • Smoothing a data set: create an approximating function that preserves patterns in the data, while leaving out noise or fine- scale structures. [Shortened from Wikipedia] • Laplacian smoothing for Naïve Bayes: argmax𝑐 𝑃 𝑐 𝑥1, … , 𝑥𝑛 ≈ argmax𝑐𝑃 𝑐 𝑃 𝑥1 𝑐 ⋯ 𝑃 𝑥𝑛 𝑐 • Smoothing for language models [ACL14] 𝑃 𝑤𝑛 𝑤𝑛−𝑘 ⋯ 𝑤𝑛−1 must not be 0 for unobserved 𝑤𝑛−𝑘 ⋯ 𝑤𝑛−1 𝑤𝑛 55 Language models smoothen probability distributions must not be 0
  • 56. • What other terms could appear in a masked position? • High “temperature” → diversity of answers • Varying answers for “Write a poem about <your name>” 56 Smoothing is the core task of Large Language Models
  • 57. 57 Sampling diverse decisions towards preferred answers 5 different answers: [Potyka23]
  • 58. Language models are not fact repositories but they are good representing commonly occurring facts. 58 Observation 4
  • 59. 6 Large Language Models as AI Assistants
  • 60. 60 Integrating Knowledge Graph Embeddings and Pre-trained Language Models in Hypercomplex Spaces [ISWC2023]
  • 61. ex:AstonVilla ex:endedWinlessStreakAgainst ex:WestHamUnited ; ex:hasConsecutiveHomeVictories 11 ; ex:hasMatch [ ex:hasScorer ex:DouglasLuiz, ex:hasScorer ex:OllieWatkins, ex:hasScorer ex:LeonBailey ] . ex:DouglasLuiz a foaf:Person ; foaf:name "Douglas Luiz" ; ex:scoresFor "sixth league game running" ; ex:scoresPenalty true ; ex:doubledTally true . ex:OllieWatkins a foaf:Person ; foaf:name "Ollie Watkins" ; ex:scoredForEngland true ; ex:pulledShotWide true . ex:WestHamUnited a ex:FootballClub . ex:JarrodBowen a foaf:Person ; foaf:name "Jarrod Bowen" ; ex:deflectedShot true . ex:JohnMcGinn a foaf:Person ; foaf:name "John McGinn" ; ex:providesAssist true . ex:KurtZouma a foaf:Person ; foaf:name "Kurt Zouma" ; ex:disrupted true . ex:MichailAntonio a foaf:Person ; foaf:name "Michail Antonio" ; ex:shotOnTarget true . ex:EmiMartinez a foaf:Person ; foaf:name "Emi Martinez" ; ex:makesSmartStop true . ex:LucasPaqueta a foaf:Person ; 61 Knowledge engineering by LLM translation
  • 62. @prefix vfb: <http://example.com/soccerclub#>. @prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>. @prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>. @prefix xsd: <http://www.w3.org/2001/XMLSchema#>. vfb:VfB rdf:type vfb:SoccerClub; vfb:hasName "VfB"; vfb:hasNickname "Brustring". vfb:SechsterErfolgInSerie rdf:type vfb:MatchResult; vfb:againstTeam vfb:UnionBerlin; vfb:withScore "3:0”. vfb:UnionBerlin rdf:type vfb:SoccerClub; vfb:hasName "1. FC Union Berlin". vfb:MaxiMittelstaedt rdf:type vfb:Player; vfb:hasName "Maxi Mittelstädt". vfb:DanAxelZagadou rdf:type vfb:Player; vfb:hasName "Dan-Axel Zagadou". vfb:PascalStenzel rdf:type vfb:Player; vfb:hasName "Pascal Stenzel". vfb:HirokiIto rdf:type vfb:Player; vfb:hasName "Hiroki Ito". vfb:SerhouGuirassy rdf:type vfb:Player; vfb:hasName "Serhou Guirassy"; vfb:hasGoals "1"; vfb:hasAssists "0". vfb:DenizUndav rdf:type vfb:Player; vfb:hasName "Deniz Undav"; vfb:hasGoals "1"; 62 Knowledge engineering by LLM translation
  • 63. 63 Few shot in context learning on KB question answering Tianle Li, Xueguang Ma, Alex Zhuang, Yu Gu, Yu Su, and Wenhu Chen. 2023. Few-shot In-context Learning on Knowledge Base Question Answering. In ACL-2023
  • 64. 64 Integration of knowledge graphs by language model [SIGIR23]
  • 65. Language models may be our translators and interfaces for assisting the entering and retrieval of facts. 65 Observation 5
  • 67. Knowing for Sure • Research required for dealing with federated, overlapping KGs with multiple authorities Knowing More • Know what you get and evaluate not only with encyclopedic KGs LLMs as knowledge bases • Commonsense knowledge • Frequently observed knowledge LLMs as AI assistants • entering and retrieving “point knowledge” Do not (always) go with the flow
  • 68. Thank you! E-Mail www. Universität Stuttgart KI – Institute for Artificial Intelligence Universitätsstraße 32, 70569 Stuttgart Steffen Staab ki.uni-stuttgart.de Analytic Computing, KI Steffen.staab@ki.uni-stuttgart.de Many thanks go to my PhD students, PostDocs and collaborators who made the work possible portrayed in this talk check out references! I hire PostDoc & PhD student for circular factory project!
  • 69. 1. [Potyka23] Nico Potyka, Yuqicheng Zhu, Evgeny Kharlamov and Steffen Staab. Uncertainty-aware Knowledge Extraction from Large Language Models using Social Choice Theory. TechReport. 2. [ISWC2022] B. Xiong, N. Potyka, T.-K. Tran, M. Nayyeri, S. Staab. For “Faithful Embeddings for EL++ Knowledge Bases”. In: 21st International Semantic Web Conference (ISWC2022) 3. [SIGIR23] J. Lu, J. Shen, B. Xiong, W. Ma, S. Staab, C. Yang. HiPrompt: Few- Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting. In: Proceedings of ACM SIGIR-2023, Taipei, Taiwan, July 23-27, 2023. 4. [ISWC2023] M. Nayyeri, Z. Wang, M. M. Akter, M. Mohtashim, Md R. Al Hasan Rony, J. Lehmann, S. Staab. Integrating Knowledge Graph Embeddings and Pre- trained Language Models in Hypercomplex Spaces. In: 22nd Int. Semantic Web Conference (ISWC2023), Athens, GR, November 6-10, 2023. 5. [TransE 2013] Bordes, Antoine, et al. "Translating embeddings for modeling multi-relational data." Advances in neural information processing systems 26 (2013). References related to Knowing More
  • 70. 1. [ISWC19] M. Leinberger, P. Seifer, C. Schon, R. Lämmel, S. Staab. Type Checking Program Code using SHACL. In: Proc. of Int. Semantic Web Conference (ISWC-2019). Auckland, New Zealand, October 2019. 2. [Seifer2023] Philipp Seifer, Daniel Hernández, Ralf Lämmel, Steffen Staab. From Shapes to Shapes: Inferring SHACL Shapes for Results of SPARQL CONSTRUCT Queries. TechReport. 3. [ESOP17] M. Leinberger, R. Lämmel, S. Staab. The essence of functional programming on semantic data. In 26th European Symposium on Programming (ESOP 2017), Uppsala, SE, 22 - 29 Apr 2017, pp. 750-776. 4. [CAAD Futures 2023] D. Elshani, D. Hernandez, A. Lombardi, L. Siriwardena, T. Schwinn, A. Fisher, S. Staab, A. Menges, T. Wortmann. Building Information Validation and Reasoning Using Semantic Web Technologies. In: Computer-Aided Architectural Design. CAAD Futures 2023. Springer, Cham, 2023. 5. [KR2020] T. Rienstra, C. Schon, S. Staab. Concept Contraction in the Description Logic EL. In: Principles of Knowledge Representation and Reasoning: Proceedings of the Seventeenth International Conference, KR 2020, pp. 723-732. 6. [EKAW18] C. Schon, S. Staab, P. Kügler, P. Kestel, B. Schleich, S. Wartzack. Metaproperty-guided Deletion from the Instance-Level of a Knowledge Base. In: Proc. of EKAW 2018, 21st International Conference on Knowledge Engineering and Knowledge Management, November 12-16, 2018, Nancy, France, Springer 2018. 7. [ESWC2013] S. Scheglmann, S. Staab, M. Thimm, G. Gröner. Locking for Concurrent Transactions on Ontologies. In: 10th Extended Semantic Web Conference (ESWC2013), Montpellier, France, May 26-30, 2013. 8. [WWW08] S. Schenk, S. Staab. Networked Graphs: A Declarative Mechanism for SPARQL Rules, SPARQL Views and RDF Data Integration on the Web. In: Proc. of WWW-2008, 17th Int. World Wide Web Conference, Bejing, China, April 21-25, 2008, pp. 585-594. References related to Knowing for Sure
  • 71. [ACL14] R. Pickhardt, T. Gottron, M. Körner, P. G. Wagner, T. Speicher, S. Staab. A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser Ney Smoothing. In: Proc. of ACL-2014 - The 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, June 22-27, 2014. 02.11.2020 Steffen Staab, Universität Stuttgart, @ststaab, https://www.ipvs.uni-stuttgart.de/departments/ac/ 71 Others

Editor's Notes

  1. If it looks like a duck, walks like a duck and quacks like a duck, then it just may be a duck. Huey, Dewey, and Louie live in Duckburg
  2. If it looks like a duck, walks like a duck and quacks like a duck, then it just may be a duck. Huey, Dewey, and Louie live in Duckburg
  3. If it looks like a duck, walks like a duck and quacks like a duck, then it just may be a duck. Huey, Dewey, and Louie live in Duckburg
  4. 750 million triples, fast growing, not easy to manage
  5. status: proposal for funding by 20 PIs, mostly engineering, mostly from KIT
  6. 7 year excellence cluster at Uni Stuttgart
  7. medical knowledge graphs and applications may be found on either side
  8. Now I am gonna to present those geometric interpretations and the corresponding loss term for each axiom. In Abox, we have two types of axioms: Concept assertion and Role assertion r(a, b). For concept assertion, the geometric interpretation is that the point of instance a should be inside the box of the class C. That means that our loss should enforce every dimension of the point a to be between the low-left corner of box C and upper-right corner of box C. We also have role assertion r(a, b) saying that a has a relation r with b, the geometric interpretation is that the point a, after a affine transformation of r, should be near the point of b. The corresponding loss term can be defined by minimizing the L2 distance between the transformed point of a and the point b. We proved that our terms satisfy the soundness guarantees that means our loss terms are zero if and only if the corresponding geometric interpretations are satisfied.
  9. Now I am gonna to present those geometric interpretations and the corresponding loss term for each axiom. In Abox, we have two types of axioms: Concept assertion and Role assertion r(a, b). For concept assertion, the geometric interpretation is that the point of instance a should be inside the box of the class C. That means that our loss should enforce every dimension of the point a to be between the low-left corner of box C and upper-right corner of box C. We also have role assertion r(a, b) saying that a has a relation r with b, the geometric interpretation is that the point a, after a affine transformation of r, should be near the point of b. The corresponding loss term can be defined by minimizing the L2 distance between the transformed point of a and the point b. We proved that our terms satisfy the soundness guarantees that means our loss terms are zero if and only if the corresponding geometric interpretations are satisfied.
  10. [Hypertext2008]
  11. Yulan talked in her keynote about voting in order to improve confidence – though I also have observed non-i.i.d. behaviour and then voting may be bad
  12. usefulness may be an issue
  13. In the following I will give you webpage content about a soccer club. Represent the facts that you find in this text in RDF turtle notation. Effizienter VfB siegt bei Union Berlin Die Siegesserie des VfB geht weiter. Beim 1. FC Union Berlin setzt sich die Mannschaft mit dem Brustring mit 3:0 durch. Es ist der sechste Erfolg in Serie und der erste gegen Union in der Bundesliga. Der Spielverlauf: Der VfB ging mit einer auf zwei Positionen veränderten Startformation in das Duell beim 1. FC Union Berlin. Maxi Mittelstädt und Dan-Axel Zagadou begannen für Pascal Stenzel sowie Hiroki Ito (beide Bank). Die Mannschaft mit dem an diesem Tag schwarzen Brustring startete selbstbewusst in die Partie und hatte in der Anfangsviertelstunde deutlich mehr Ballbesitz. Die höheren Spielanteile münzte der VfB schnell in die verdiente Führung um. Wer sonst als Serhou Guirassy hätte der Torschütze zum 1:0 sein können (siehe „Die Tore“). Die Jungs aus Cannstatt kontrollierten die Partie auch in der Folge, musste nach knapp einer halben Stunde aber schon wechseln. Serhou Guirassy verließ den Platz angeschlagen mit muskulären Problemen im hinteren linken Oberschenkel, Deniz Undav kam für ihn in die Partie. Der VfB war dennoch bis zum Pausenpfiff das tonangebende Team. Silas und Deniz Undav sorgen für die Entscheidung Nach dem Wiederanpfiff entwickelte sich eine umkämpfte Partie mit vielen Situationen zwischen den Strafräumen. Klare Torchancen konnte sich zunächst keines der Teams erspielen. In der 60. Minute hatte Jamie Leweling jedoch die große Chance, auf 2:0 zu erhöhen. Der 22-Jährige scheiterte in aussichtsreicher Position frei vor dem Tor an Unions Torhüter Frederik Rönnow. In der 77. Minute war Alexander Nübel auf der Gegenseite hellwach und klärte die Situation gegen den heranstürmenden Kevin Behrens. Kurz darauf sorgte der VfB mit einem Konter für das beruhigende 2:0. Der eingewechselte Silas war mit seinem dritten Saisontor erfolgreich. Den Endstand zum 3:0 stellte Deniz Undav mit einem Kopfball her. Der VfB siegte am Ende verdient, weil er seine Chancen konsequent nutzte und über die gesamte Spielzeit hinweg kaum Chancen des Gegners zuließ. Den gesamten Spielverlauf im VfB-Liveticker nachlesen. Die Tore: 16. Minute: Serhou Guirassy köpft nach einer Flanke von Anthony Rouault zum 1:0 ein. Es ist das 14. Saisontor des VfB-Stürmers. 81. Minute: Silas kommt über Karazor und Millot an den Ball, setzt sich gegen die aufgerückten Union-Verteidiger durch und schließt überlegt zum 2:0 ab. 88. Minute: Der VfB erobert in Höhe des gegnerischen Strafraums den Ball, Wooyeong Jeong flankt von rechts auf Deniz Undav, der zentral zum 3:0 einköpft. Die Stimmen: VfB-Cheftrainer Sebastian Hoeneß: „Es war eine reife Leistung von uns. Wir haben sehr erwachsen gespielt. Die Druckphasen des Gegners waren nie so sehr ausgeprägt. Dass wir das Spiel am Ende so klar auf unsere Seite ziehen, macht mich stolz. Wir haben aktuell einen Lauf und den wollen wir so lange wie möglich mitnehmen.“ Chris Führich: „Es war eine Riesenteamleistung von uns. Wir wussten, wie schwierig es ist, hier zu gewinnen. Wir haben von der ersten bis zur letzten Minute unsere Taktik durchgezogen. Es ist auch sehr wichtig gegen die lange Bälle und wuchtigen Spieler von Union gut zu stehen. Das ist uns gut gelungen und wir haben letztlich auch verdient gewonnen.“ Maxi Mittelstädt: „Es ist ein schönes Gefühl, dass wir gewonnen haben. Wir haben eine reife Leistung gezeigt und wenig anbrennen lassen. Natürlich gab es auch Phasen, die wir überstehen mussten. Wir haben einen breiten und starken Kader. Auch heute war wichtig, welche Impulse die Einwechselspieler in die Partie gebracht haben. Das Kollektiv macht uns aktuell stark. Manchmal muss man sich angesichts der Siegesserie kneifen, aber wir haben uns das auch über die vergangenen Monate und Wochen erarbeitet. Ich freue mich auf die kommenden Herausforderungen.“ Die Besonderheiten: Der gebürtige Berliner Maximilian Mittelstädt gab sein Startelfdebüt für den VfB. Neu-Nationalspieler Chris Führich machte an diesem Samstag sein 75. Pflichtspiel im Trikot mit dem roten Brustring. Der ehemalige VfBler Rani Khedira gab auf Seiten der Berliner gegen den Club aus Cannstatt sein Comeback nach einer längeren Wadenverletzung. Der Schiedsrichter der Partie Bastian Dankert und seine Assistenz René Rohde leiteten ihr jeweils 150. Bundesligaspiel. 21 Punkte nach acht Spieltagen hat der VfB in seiner Vereinshistorie noch nie auf dem Konto gehabt. Die nächsten Spiele: Am kommenden Samstag empfängt der VfB die TSG Hoffenheim in der MHPArena. Dieses Spiel ist bereits ausverkauft, ebenso wie die Heimpartie gegen Borussia Dortmund am 11. November. Der Mitgliedervorverkauf für das Pokal-Heimspiel gegen den 1. FC Union Berlin am Dienstagabend, 31. Oktober, 18 Uhr läuft, genauso wie für die Heimbegegnung gegen den SV Werder Bremen am Samstag, 2. Dezember, 18:30 Uhr. Zum VfB-Onlineshop.
  14. emory university and google