SlideShare una empresa de Scribd logo
1 de 72
Descargar para leer sin conexión
05/29/23 Heiko Paulheim 1
Knowledge Graph Generation
from Wikipedia in the Age of ChatGPT:
Knowledge Extraction
or Knowledge Hallucination?
Heiko Paulheim
05/29/23 Heiko Paulheim 2
Yeah, I’ve been Invited for this Keynote!
05/29/23 Heiko Paulheim 3
A Brief History of Knowledge Graphs
Google’s
Announcement
DBpedia
YAGO
ResearchCyc Wikidata
Freebase
NELL
05/29/23 Heiko Paulheim 4
A Brief History of Knowledge Graphs
05/29/23 Heiko Paulheim 5
Wikipedia as a Knowledge Graph
• Wikipedia based Knowledge Graphs
– DBpedia: launched 2007
– YAGO: launched 2008
– Extraction from Wikipedia
using mappings & heuristics
• Present
– Two of the most used knowledge graphs
– ...with Wikidata catching up
05/29/23 Heiko Paulheim 6
Wikipedia as a Knowledge Graph
05/29/23 Heiko Paulheim 7
Wikipedia as a Knowledge Graph
city
campus
state
c
i
t
y
05/29/23 Heiko Paulheim 8
Wikipedia as a Knowledge Graph
• Mapping to a central schema/ontology
University
chancellor Person
Organisation
Agent
campus Place
range
range
domain
domain
subclass of
subclass of
subclass of
05/29/23 Heiko Paulheim 9
Wikipedia as a Knowledge Graph
05/29/23 Heiko Paulheim 10
DBpedia Extraction, ChatGPT Style
05/29/23 Heiko Paulheim 11
DBpedia Extraction, ChatGPT Style
05/29/23 Heiko Paulheim 12
DBpedia Extraction, ChatGPT Style
05/29/23 Heiko Paulheim 13
DBpedia Extraction, ChatGPT Style
• Looks nice, but there are some glitches…
– Handling datatypes:
– Handling coordinates:
• But maybe we can resolve this with better prompt engineering...
05/29/23 Heiko Paulheim 14
DBpedia Extraction, ChatGPT Style
;
05/29/23 Heiko Paulheim 15
DBpedia Extraction, ChatGPT Style
05/29/23 Heiko Paulheim 16
Knowledge Graph Completion, ChatGPT Style
05/29/23 Heiko Paulheim 17
Knowledge Graph Hallucination, ChatGPT Style
• Some more findings:
• None of those are real!
• cf. DBpedia:
05/29/23 Heiko Paulheim 18
Knowledge Graph Completion, ChatGPT Style
05/29/23 Heiko Paulheim 19
Knowledge Graph Hallucination, ChatGPT Style
05/29/23 Heiko Paulheim 20
Knowledge Graph Hallucination, ChatGPT Style
• My first reaction: • My second reaction:
05/29/23 Heiko Paulheim 21
Knowledge Graph Hallucination, ChatGPT Style
Mannheim is a city in the southwestern part of
Germany, the third-largest in the German state of
Baden-Württemberg after Stuttgart and Karlsruhe with a
2019 population of approximately 309,000 inhabitants.
05/29/23 Heiko Paulheim 22
But While We’re at it...
• Hey ChatGPT, did you know this paper?
05/29/23 Heiko Paulheim 23
Back to my Original Presentation
05/29/23 Heiko Paulheim 24
Flashback to 2018
• Much of the missing information is in the Wikipedia text
• ...and already in the abstracts
• Abstracts follow a structure
municipality state country
+
+
-
-
05/29/23 Heiko Paulheim 25
Flashback to 2018
• The first three populated places linked in an abstract about a town
are that town’s municipality, state, and country
• All genres linked in an abstract about a writer
are that writer’s genres
• The first place linked in an abstract about a person
is that person’s birthplace
• The types are already in DBpedia
• Automatically finding those patterns:
We can use existing relations as training data
– Using a local closed world assumption for creating negative examples
05/29/23 Heiko Paulheim 26
Flashback to 2018
• Target: use only models that have >95% precision
– We want extra knowledge, but not much extra noise
• Outcome
– Models could be learned for 99 relations
– Almost 1M additional statements
05/29/23 Heiko Paulheim 27
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 28
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 29
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
Only the first three
facts are extracted
from the abstract
05/29/23 Heiko Paulheim 30
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
DBpedia uses
dbo:federalState here
05/29/23 Heiko Paulheim 31
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
• In the original paper, we trained general ML models...
05/29/23 Heiko Paulheim 32
Flashback to 2018
• We used solely position and type features
– Nothing language specific
– i.e.: we can apply this to any language
• Extension to 12 largest language editions of DBpedia
– Exploiting inter-language links
– 187 relations (was: 99), 1.6M axioms (was: 1M), at precision >0.95
– #statements per language correlates with #language links to English!
05/29/23 Heiko Paulheim 33
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 34
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 35
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 36
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
• Let’s challenge ChatGPT a bit more...
05/29/23 Heiko Paulheim 37
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 38
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
Mostly hallucination…
this is not the population
value from the abstract!
05/29/23 Heiko Paulheim 39
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 40
Relation Extraction from Wikipedia Abstracts:
ChatGPT Style
05/29/23 Heiko Paulheim 41
Knowledge Graph Hallucination, ChatGPT Style
• ChatGPT seemed to be eager on “extracting” coordinates from
infoboxes and abstracts
05/29/23 Heiko Paulheim 42
Knowledge Graph Hallucination, ChatGPT Style
• At least, all are different coordinates in Mannheim
05/29/23 Heiko Paulheim 43
Funny Footnote –
Even more Knowledge Hallucination
• Trying to create the input file for Google Map on the previous slide:
Even more hallucination…
many of these values
are not
from the responses
05/29/23 Heiko Paulheim 44
Back to my Original Presentation
05/29/23 Heiko Paulheim 45
Cat2Ax: Axiomatizing Wikipedia Categories
 dbo:Album
 dbo:artist.{dbr:Nine_Inch_Nails}
 dbo:genre.{dbr:Rock_Music}
See: ISWC 2019 Paper on Uncovering the Semantics of Wikipedia Categories
05/29/23 Heiko Paulheim 46
Cat2Ax: Axiomatizing Wikipedia Categories
– Frequency: how often does the pattern occur in a category?
• i.e.: share of instances that have dbo:genre.{dbr.Rock_Music}?
– Lexical score: likelihood of term as a surface form of object
• i.e.: how often is Rock used to refer to dbr:Rock_Music?
– Sibling score: how likely are sibling categories sharing similar patterns?
• i.e., are there sibling categories with a high score for dbo:genre?
05/29/23 Heiko Paulheim 47
Cat2Ax: ChatGPT Style
05/29/23 Heiko Paulheim 48
Cat2Ax: ChatGPT Style
05/29/23 Heiko Paulheim 49
Cat2Ax: ChatGPT Style
05/29/23 Heiko Paulheim 50
Cat2Ax: ChatGPT Style
05/29/23 Heiko Paulheim 51
CaLiGraph Example
Category: Musical Groups established
in 1987
List of symphonic metal bands
Category: Swedish death metal bands
List of Swedes in Music
05/29/23 Heiko Paulheim 52
CaLiGraph: ChatGPT Style
05/29/23 Heiko Paulheim 53
CaLiGraph: ChatGPT Style
05/29/23 Heiko Paulheim 54
CaLiGraph: ChatGPT Style
05/29/23 Heiko Paulheim 55
Back to my Original Presentation
05/29/23 Heiko Paulheim 56
Improving Entity Coverage:
Lists in Wikipedia
• Only existing pages have categories
– Lists may also link to non-existing pages
05/29/23 Heiko Paulheim 57
Pushing Entity Coverage Further
• Beyond red links (2020) • Beyond explicit lists (2021)
05/29/23 Heiko Paulheim 58
Cat2Ax: ChatGPT Style
05/29/23 Heiko Paulheim 59
Entity Extraction from Listings: ChatGPT Style
05/29/23 Heiko Paulheim 60
Entity Extraction from Listings: ChatGPT Style
05/29/23 Heiko Paulheim 61
Entity Extraction from Listings: ChatGPT Style
05/29/23 Heiko Paulheim 62
Entity Hallucination from Listings:
ChatGPT goes Rogue
05/29/23 Heiko Paulheim 63
Entity Hallucination from Listings:
ChatGPT goes Rogue
05/29/23 Heiko Paulheim 64
Entity Hallucination from Listings:
ChatGPT goes Rogue
05/29/23 Heiko Paulheim 65
Entity Hallucination from Listings:
ChatGPT goes Rogue
05/29/23 Heiko Paulheim 66
Entity Hallucination from Listings:
ChatGPT goes Rogue
This went on for a while, but lead nowhere.
05/29/23 Heiko Paulheim 67
Revisiting CaLiGraph: Entity Disambiguation
• Examples: Wikipedia pages of Die Krupps and Eisbrecher
?
05/29/23 Heiko Paulheim 68
Revisiting CaLiGraph: Entity Disambiguation
Proper solution:
”NASTyLinker: NIL-Aware Scalable
Transformer-based Entity Linker”
Tuesday, 12 am
05/29/23 Heiko Paulheim 69
Entity Disambiguation: ChatGPT Bloopers
05/29/23 Heiko Paulheim 70
Entity Disambiguation: ChatGPT Bloopers
05/29/23 Heiko Paulheim 71
Take Aways
• Basic KG creation with ChatGPT can work
– At least in a human in the loop setup
• Reinforcement signals might help here
– Main challenge: hallucinations
• On the other hand: consider them
“extraction of additional facts”
• Isn’t that just like heuristic KG completion?
• Disclaimer:
– No PhD students were harmed or replaced by ChatGPT.
• Full ChatGPT protocol available here.
05/29/23 Heiko Paulheim 72
Knowledge Graph Generation
from Wikipedia in the Age of ChatGPT:
Knowledge Extraction
or Knowledge Hallucination?
Heiko Paulheim

Más contenido relacionado

La actualidad más candente

Explainable AI in Industry (KDD 2019 Tutorial)
Explainable AI in Industry (KDD 2019 Tutorial)Explainable AI in Industry (KDD 2019 Tutorial)
Explainable AI in Industry (KDD 2019 Tutorial)
Krishnaram Kenthapadi
 

La actualidad más candente (20)

Generative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptxGenerative AI, WiDS 2023.pptx
Generative AI, WiDS 2023.pptx
 
LanGCHAIN Framework
LanGCHAIN FrameworkLanGCHAIN Framework
LanGCHAIN Framework
 
Improving Machine Learning using Graph Algorithms
Improving Machine Learning using Graph AlgorithmsImproving Machine Learning using Graph Algorithms
Improving Machine Learning using Graph Algorithms
 
Copilot to Cover: Why AI can't replace developers with robots, but can make l...
Copilot to Cover: Why AI can't replace developers with robots, but can make l...Copilot to Cover: Why AI can't replace developers with robots, but can make l...
Copilot to Cover: Why AI can't replace developers with robots, but can make l...
 
Using the power of Generative AI at scale
Using the power of Generative AI at scaleUsing the power of Generative AI at scale
Using the power of Generative AI at scale
 
How Kafka Powers the World's Most Popular Vector Database System with Charles...
How Kafka Powers the World's Most Popular Vector Database System with Charles...How Kafka Powers the World's Most Popular Vector Database System with Charles...
How Kafka Powers the World's Most Popular Vector Database System with Charles...
 
Neo4j Graph Use Cases, Bruno Ungermann, Neo4j
Neo4j Graph Use Cases, Bruno Ungermann, Neo4jNeo4j Graph Use Cases, Bruno Ungermann, Neo4j
Neo4j Graph Use Cases, Bruno Ungermann, Neo4j
 
Property graph vs. RDF Triplestore comparison in 2020
Property graph vs. RDF Triplestore comparison in 2020Property graph vs. RDF Triplestore comparison in 2020
Property graph vs. RDF Triplestore comparison in 2020
 
Log System As Backbone – How We Built the World’s Most Advanced Vector Databa...
Log System As Backbone – How We Built the World’s Most Advanced Vector Databa...Log System As Backbone – How We Built the World’s Most Advanced Vector Databa...
Log System As Backbone – How We Built the World’s Most Advanced Vector Databa...
 
Journey of Generative AI
Journey of Generative AIJourney of Generative AI
Journey of Generative AI
 
Hadoop Overview & Architecture
Hadoop Overview & Architecture  Hadoop Overview & Architecture
Hadoop Overview & Architecture
 
Transfer Learning for Natural Language Processing
Transfer Learning for Natural Language ProcessingTransfer Learning for Natural Language Processing
Transfer Learning for Natural Language Processing
 
Graph databases
Graph databasesGraph databases
Graph databases
 
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdfNeo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
Neo4j Generative AI workshop at GraphSummit London 14 Nov 2023.pdf
 
Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)Neural Text Embeddings for Information Retrieval (WSDM 2017)
Neural Text Embeddings for Information Retrieval (WSDM 2017)
 
GPT and Graph Data Science to power your Knowledge Graph
GPT and Graph Data Science to power your Knowledge GraphGPT and Graph Data Science to power your Knowledge Graph
GPT and Graph Data Science to power your Knowledge Graph
 
Querying the Wikidata Knowledge Graph
Querying the Wikidata Knowledge GraphQuerying the Wikidata Knowledge Graph
Querying the Wikidata Knowledge Graph
 
openai-chatgpt sunumu
openai-chatgpt sunumuopenai-chatgpt sunumu
openai-chatgpt sunumu
 
Seldon: Deploying Models at Scale
Seldon: Deploying Models at ScaleSeldon: Deploying Models at Scale
Seldon: Deploying Models at Scale
 
Explainable AI in Industry (KDD 2019 Tutorial)
Explainable AI in Industry (KDD 2019 Tutorial)Explainable AI in Industry (KDD 2019 Tutorial)
Explainable AI in Industry (KDD 2019 Tutorial)
 

Similar a Knowledge Graph Generation from Wikipedia in the Age of ChatGPT: Knowledge Extraction or Knowledge Hallucination?

Copyright 2019. tran
Copyright  2019. tranCopyright  2019. tran
Copyright 2019. tran
AlleneMcclendon878
 
Beyond DBpedia and YAGO – The New Kids on the Knowledge Graph Block
Beyond DBpedia and YAGO – The New Kids  on the Knowledge Graph BlockBeyond DBpedia and YAGO – The New Kids  on the Knowledge Graph Block
Beyond DBpedia and YAGO – The New Kids on the Knowledge Graph Block
Heiko Paulheim
 

Similar a Knowledge Graph Generation from Wikipedia in the Age of ChatGPT: Knowledge Extraction or Knowledge Hallucination? (8)

From Wikis to Knowledge Graphs
From Wikis to Knowledge GraphsFrom Wikis to Knowledge Graphs
From Wikis to Knowledge Graphs
 
Machine Learning with and for Semantic Web Knowledge Graphs
Machine Learning with and for Semantic Web Knowledge GraphsMachine Learning with and for Semantic Web Knowledge Graphs
Machine Learning with and for Semantic Web Knowledge Graphs
 
Towards Knowledge Graph Profiling
Towards Knowledge Graph ProfilingTowards Knowledge Graph Profiling
Towards Knowledge Graph Profiling
 
From Wikipedia to Thousands of Wikis – The DBkWik Knowledge Graph
From Wikipedia to Thousands of Wikis – The DBkWik Knowledge GraphFrom Wikipedia to Thousands of Wikis – The DBkWik Knowledge Graph
From Wikipedia to Thousands of Wikis – The DBkWik Knowledge Graph
 
Knowledge Graphs on the Web
Knowledge Graphs on the WebKnowledge Graphs on the Web
Knowledge Graphs on the Web
 
Copyright 2019. tran
Copyright  2019. tranCopyright  2019. tran
Copyright 2019. tran
 
Beyond DBpedia and YAGO – The New Kids on the Knowledge Graph Block
Beyond DBpedia and YAGO – The New Kids  on the Knowledge Graph BlockBeyond DBpedia and YAGO – The New Kids  on the Knowledge Graph Block
Beyond DBpedia and YAGO – The New Kids on the Knowledge Graph Block
 
Big Data, Smart Algorithms, and Market Power - A Computer Scientist's Perspec...
Big Data, Smart Algorithms, and Market Power - A Computer Scientist's Perspec...Big Data, Smart Algorithms, and Market Power - A Computer Scientist's Perspec...
Big Data, Smart Algorithms, and Market Power - A Computer Scientist's Perspec...
 

Más de Heiko Paulheim

Más de Heiko Paulheim (20)

New Adventures in RDF2vec
New Adventures in RDF2vecNew Adventures in RDF2vec
New Adventures in RDF2vec
 
New Adventures in RDF2vec
New Adventures in RDF2vecNew Adventures in RDF2vec
New Adventures in RDF2vec
 
Knowledge Matters! The Role of Knowledge Graphs in Modern AI Systems
Knowledge Matters! The Role of Knowledge Graphs in Modern AI SystemsKnowledge Matters! The Role of Knowledge Graphs in Modern AI Systems
Knowledge Matters! The Role of Knowledge Graphs in Modern AI Systems
 
Using Knowledge Graphs in Data Science - From Symbolic to Latent Representati...
Using Knowledge Graphs in Data Science - From Symbolic to Latent Representati...Using Knowledge Graphs in Data Science - From Symbolic to Latent Representati...
Using Knowledge Graphs in Data Science - From Symbolic to Latent Representati...
 
Big Data, Smart Algorithms, and Market Power - A Computer Scientist’s Perspec...
Big Data, Smart Algorithms, and Market Power - A Computer Scientist’s Perspec...Big Data, Smart Algorithms, and Market Power - A Computer Scientist’s Perspec...
Big Data, Smart Algorithms, and Market Power - A Computer Scientist’s Perspec...
 
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
 
Make Embeddings Semantic Again!
Make Embeddings Semantic Again!Make Embeddings Semantic Again!
Make Embeddings Semantic Again!
 
How much is a Triple?
How much is a Triple?How much is a Triple?
How much is a Triple?
 
Weakly Supervised Learning for Fake News Detection on Twitter
Weakly Supervised Learning for Fake News Detection on TwitterWeakly Supervised Learning for Fake News Detection on Twitter
Weakly Supervised Learning for Fake News Detection on Twitter
 
Data-driven Joint Debugging of the DBpedia Mappings and Ontology
Data-driven Joint Debugging of the DBpedia Mappings and OntologyData-driven Joint Debugging of the DBpedia Mappings and Ontology
Data-driven Joint Debugging of the DBpedia Mappings and Ontology
 
Fast Approximate A-box Consistency Checking using Machine Learning
Fast Approximate  A-box Consistency Checking using Machine LearningFast Approximate  A-box Consistency Checking using Machine Learning
Fast Approximate A-box Consistency Checking using Machine Learning
 
Serving DBpedia with DOLCE - More Than Just Adding a Cherry on Top
Serving DBpedia with DOLCE - More Than Just Adding a Cherry on TopServing DBpedia with DOLCE - More Than Just Adding a Cherry on Top
Serving DBpedia with DOLCE - More Than Just Adding a Cherry on Top
 
Combining Ontology Matchers via Anomaly Detection
Combining Ontology Matchers via Anomaly DetectionCombining Ontology Matchers via Anomaly Detection
Combining Ontology Matchers via Anomaly Detection
 
Gathering Alternative Surface Forms for DBpedia Entities
Gathering Alternative Surface Forms for DBpedia EntitiesGathering Alternative Surface Forms for DBpedia Entities
Gathering Alternative Surface Forms for DBpedia Entities
 
What the Adoption of schema.org Tells about Linked Open Data
What the Adoption of schema.org Tells about Linked Open DataWhat the Adoption of schema.org Tells about Linked Open Data
What the Adoption of schema.org Tells about Linked Open Data
 
Linked Open Data enhanced Knowledge Discovery
Linked Open Data enhanced  Knowledge DiscoveryLinked Open Data enhanced  Knowledge Discovery
Linked Open Data enhanced Knowledge Discovery
 
Mining the Web of Linked Data with RapidMiner
Mining the Web of Linked Data with RapidMinerMining the Web of Linked Data with RapidMiner
Mining the Web of Linked Data with RapidMiner
 
Data Mining with Background Knowledge from the Web - Introducing the RapidMin...
Data Mining with Background Knowledge from the Web - Introducing the RapidMin...Data Mining with Background Knowledge from the Web - Introducing the RapidMin...
Data Mining with Background Knowledge from the Web - Introducing the RapidMin...
 
Detecting Incorrect Numerical Data in DBpedia
Detecting Incorrect Numerical Data in DBpediaDetecting Incorrect Numerical Data in DBpedia
Detecting Incorrect Numerical Data in DBpedia
 
Identifying Wrong Links between Datasets by Multi-dimensional Outlier Detection
Identifying Wrong Links between Datasets by Multi-dimensional Outlier DetectionIdentifying Wrong Links between Datasets by Multi-dimensional Outlier Detection
Identifying Wrong Links between Datasets by Multi-dimensional Outlier Detection
 

Último

➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
amitlee9823
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
gajnagarg
 
Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...
gajnagarg
 
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night StandCall Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
amitlee9823
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
gajnagarg
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
amitlee9823
 
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
amitlee9823
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
gajnagarg
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
only4webmaster01
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 

Último (20)

Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
 
Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls Bellary Escorts ☎️9352988975 Two shot with one girl ...
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night StandCall Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
 
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Marol Naka Call On 9920725232 With Body to body massage...
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls Palakkad Escorts ☎️9352988975 Two shot with one girl...
 
Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
Just Call Vip call girls Erode Escorts ☎️9352988975 Two shot with one girl (E...
 
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Junnasandra Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
Predicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science ProjectPredicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science Project
 

Knowledge Graph Generation from Wikipedia in the Age of ChatGPT: Knowledge Extraction or Knowledge Hallucination?

  • 1. 05/29/23 Heiko Paulheim 1 Knowledge Graph Generation from Wikipedia in the Age of ChatGPT: Knowledge Extraction or Knowledge Hallucination? Heiko Paulheim
  • 2. 05/29/23 Heiko Paulheim 2 Yeah, I’ve been Invited for this Keynote!
  • 3. 05/29/23 Heiko Paulheim 3 A Brief History of Knowledge Graphs Google’s Announcement DBpedia YAGO ResearchCyc Wikidata Freebase NELL
  • 4. 05/29/23 Heiko Paulheim 4 A Brief History of Knowledge Graphs
  • 5. 05/29/23 Heiko Paulheim 5 Wikipedia as a Knowledge Graph • Wikipedia based Knowledge Graphs – DBpedia: launched 2007 – YAGO: launched 2008 – Extraction from Wikipedia using mappings & heuristics • Present – Two of the most used knowledge graphs – ...with Wikidata catching up
  • 6. 05/29/23 Heiko Paulheim 6 Wikipedia as a Knowledge Graph
  • 7. 05/29/23 Heiko Paulheim 7 Wikipedia as a Knowledge Graph city campus state c i t y
  • 8. 05/29/23 Heiko Paulheim 8 Wikipedia as a Knowledge Graph • Mapping to a central schema/ontology University chancellor Person Organisation Agent campus Place range range domain domain subclass of subclass of subclass of
  • 9. 05/29/23 Heiko Paulheim 9 Wikipedia as a Knowledge Graph
  • 10. 05/29/23 Heiko Paulheim 10 DBpedia Extraction, ChatGPT Style
  • 11. 05/29/23 Heiko Paulheim 11 DBpedia Extraction, ChatGPT Style
  • 12. 05/29/23 Heiko Paulheim 12 DBpedia Extraction, ChatGPT Style
  • 13. 05/29/23 Heiko Paulheim 13 DBpedia Extraction, ChatGPT Style • Looks nice, but there are some glitches… – Handling datatypes: – Handling coordinates: • But maybe we can resolve this with better prompt engineering...
  • 14. 05/29/23 Heiko Paulheim 14 DBpedia Extraction, ChatGPT Style ;
  • 15. 05/29/23 Heiko Paulheim 15 DBpedia Extraction, ChatGPT Style
  • 16. 05/29/23 Heiko Paulheim 16 Knowledge Graph Completion, ChatGPT Style
  • 17. 05/29/23 Heiko Paulheim 17 Knowledge Graph Hallucination, ChatGPT Style • Some more findings: • None of those are real! • cf. DBpedia:
  • 18. 05/29/23 Heiko Paulheim 18 Knowledge Graph Completion, ChatGPT Style
  • 19. 05/29/23 Heiko Paulheim 19 Knowledge Graph Hallucination, ChatGPT Style
  • 20. 05/29/23 Heiko Paulheim 20 Knowledge Graph Hallucination, ChatGPT Style • My first reaction: • My second reaction:
  • 21. 05/29/23 Heiko Paulheim 21 Knowledge Graph Hallucination, ChatGPT Style Mannheim is a city in the southwestern part of Germany, the third-largest in the German state of Baden-Württemberg after Stuttgart and Karlsruhe with a 2019 population of approximately 309,000 inhabitants.
  • 22. 05/29/23 Heiko Paulheim 22 But While We’re at it... • Hey ChatGPT, did you know this paper?
  • 23. 05/29/23 Heiko Paulheim 23 Back to my Original Presentation
  • 24. 05/29/23 Heiko Paulheim 24 Flashback to 2018 • Much of the missing information is in the Wikipedia text • ...and already in the abstracts • Abstracts follow a structure municipality state country + + - -
  • 25. 05/29/23 Heiko Paulheim 25 Flashback to 2018 • The first three populated places linked in an abstract about a town are that town’s municipality, state, and country • All genres linked in an abstract about a writer are that writer’s genres • The first place linked in an abstract about a person is that person’s birthplace • The types are already in DBpedia • Automatically finding those patterns: We can use existing relations as training data – Using a local closed world assumption for creating negative examples
  • 26. 05/29/23 Heiko Paulheim 26 Flashback to 2018 • Target: use only models that have >95% precision – We want extra knowledge, but not much extra noise • Outcome – Models could be learned for 99 relations – Almost 1M additional statements
  • 27. 05/29/23 Heiko Paulheim 27 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 28. 05/29/23 Heiko Paulheim 28 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 29. 05/29/23 Heiko Paulheim 29 Relation Extraction from Wikipedia Abstracts: ChatGPT Style Only the first three facts are extracted from the abstract
  • 30. 05/29/23 Heiko Paulheim 30 Relation Extraction from Wikipedia Abstracts: ChatGPT Style DBpedia uses dbo:federalState here
  • 31. 05/29/23 Heiko Paulheim 31 Relation Extraction from Wikipedia Abstracts: ChatGPT Style • In the original paper, we trained general ML models...
  • 32. 05/29/23 Heiko Paulheim 32 Flashback to 2018 • We used solely position and type features – Nothing language specific – i.e.: we can apply this to any language • Extension to 12 largest language editions of DBpedia – Exploiting inter-language links – 187 relations (was: 99), 1.6M axioms (was: 1M), at precision >0.95 – #statements per language correlates with #language links to English!
  • 33. 05/29/23 Heiko Paulheim 33 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 34. 05/29/23 Heiko Paulheim 34 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 35. 05/29/23 Heiko Paulheim 35 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 36. 05/29/23 Heiko Paulheim 36 Relation Extraction from Wikipedia Abstracts: ChatGPT Style • Let’s challenge ChatGPT a bit more...
  • 37. 05/29/23 Heiko Paulheim 37 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 38. 05/29/23 Heiko Paulheim 38 Relation Extraction from Wikipedia Abstracts: ChatGPT Style Mostly hallucination… this is not the population value from the abstract!
  • 39. 05/29/23 Heiko Paulheim 39 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 40. 05/29/23 Heiko Paulheim 40 Relation Extraction from Wikipedia Abstracts: ChatGPT Style
  • 41. 05/29/23 Heiko Paulheim 41 Knowledge Graph Hallucination, ChatGPT Style • ChatGPT seemed to be eager on “extracting” coordinates from infoboxes and abstracts
  • 42. 05/29/23 Heiko Paulheim 42 Knowledge Graph Hallucination, ChatGPT Style • At least, all are different coordinates in Mannheim
  • 43. 05/29/23 Heiko Paulheim 43 Funny Footnote – Even more Knowledge Hallucination • Trying to create the input file for Google Map on the previous slide: Even more hallucination… many of these values are not from the responses
  • 44. 05/29/23 Heiko Paulheim 44 Back to my Original Presentation
  • 45. 05/29/23 Heiko Paulheim 45 Cat2Ax: Axiomatizing Wikipedia Categories  dbo:Album  dbo:artist.{dbr:Nine_Inch_Nails}  dbo:genre.{dbr:Rock_Music} See: ISWC 2019 Paper on Uncovering the Semantics of Wikipedia Categories
  • 46. 05/29/23 Heiko Paulheim 46 Cat2Ax: Axiomatizing Wikipedia Categories – Frequency: how often does the pattern occur in a category? • i.e.: share of instances that have dbo:genre.{dbr.Rock_Music}? – Lexical score: likelihood of term as a surface form of object • i.e.: how often is Rock used to refer to dbr:Rock_Music? – Sibling score: how likely are sibling categories sharing similar patterns? • i.e., are there sibling categories with a high score for dbo:genre?
  • 47. 05/29/23 Heiko Paulheim 47 Cat2Ax: ChatGPT Style
  • 48. 05/29/23 Heiko Paulheim 48 Cat2Ax: ChatGPT Style
  • 49. 05/29/23 Heiko Paulheim 49 Cat2Ax: ChatGPT Style
  • 50. 05/29/23 Heiko Paulheim 50 Cat2Ax: ChatGPT Style
  • 51. 05/29/23 Heiko Paulheim 51 CaLiGraph Example Category: Musical Groups established in 1987 List of symphonic metal bands Category: Swedish death metal bands List of Swedes in Music
  • 52. 05/29/23 Heiko Paulheim 52 CaLiGraph: ChatGPT Style
  • 53. 05/29/23 Heiko Paulheim 53 CaLiGraph: ChatGPT Style
  • 54. 05/29/23 Heiko Paulheim 54 CaLiGraph: ChatGPT Style
  • 55. 05/29/23 Heiko Paulheim 55 Back to my Original Presentation
  • 56. 05/29/23 Heiko Paulheim 56 Improving Entity Coverage: Lists in Wikipedia • Only existing pages have categories – Lists may also link to non-existing pages
  • 57. 05/29/23 Heiko Paulheim 57 Pushing Entity Coverage Further • Beyond red links (2020) • Beyond explicit lists (2021)
  • 58. 05/29/23 Heiko Paulheim 58 Cat2Ax: ChatGPT Style
  • 59. 05/29/23 Heiko Paulheim 59 Entity Extraction from Listings: ChatGPT Style
  • 60. 05/29/23 Heiko Paulheim 60 Entity Extraction from Listings: ChatGPT Style
  • 61. 05/29/23 Heiko Paulheim 61 Entity Extraction from Listings: ChatGPT Style
  • 62. 05/29/23 Heiko Paulheim 62 Entity Hallucination from Listings: ChatGPT goes Rogue
  • 63. 05/29/23 Heiko Paulheim 63 Entity Hallucination from Listings: ChatGPT goes Rogue
  • 64. 05/29/23 Heiko Paulheim 64 Entity Hallucination from Listings: ChatGPT goes Rogue
  • 65. 05/29/23 Heiko Paulheim 65 Entity Hallucination from Listings: ChatGPT goes Rogue
  • 66. 05/29/23 Heiko Paulheim 66 Entity Hallucination from Listings: ChatGPT goes Rogue This went on for a while, but lead nowhere.
  • 67. 05/29/23 Heiko Paulheim 67 Revisiting CaLiGraph: Entity Disambiguation • Examples: Wikipedia pages of Die Krupps and Eisbrecher ?
  • 68. 05/29/23 Heiko Paulheim 68 Revisiting CaLiGraph: Entity Disambiguation Proper solution: ”NASTyLinker: NIL-Aware Scalable Transformer-based Entity Linker” Tuesday, 12 am
  • 69. 05/29/23 Heiko Paulheim 69 Entity Disambiguation: ChatGPT Bloopers
  • 70. 05/29/23 Heiko Paulheim 70 Entity Disambiguation: ChatGPT Bloopers
  • 71. 05/29/23 Heiko Paulheim 71 Take Aways • Basic KG creation with ChatGPT can work – At least in a human in the loop setup • Reinforcement signals might help here – Main challenge: hallucinations • On the other hand: consider them “extraction of additional facts” • Isn’t that just like heuristic KG completion? • Disclaimer: – No PhD students were harmed or replaced by ChatGPT. • Full ChatGPT protocol available here.
  • 72. 05/29/23 Heiko Paulheim 72 Knowledge Graph Generation from Wikipedia in the Age of ChatGPT: Knowledge Extraction or Knowledge Hallucination? Heiko Paulheim