SlideShare ist ein Scribd-Unternehmen logo
1 von 19
Downloaden Sie, um offline zu lesen
Crafting a Knowledge Graph Strategy
What to think about
Panos Alexopoulos
Head of Ontology
2.5 years ago I got a mission ...
• “Good morning Mr. Alexopoulos. Your mission,
should you decide to accept it, is to build an
HR and Recruitment Knowledge Graph.”
• “As always, should you or any member of your
team be caught or killed, the company will
disavow any knowledge of your actions. “
• “This tape will self-destruct in 5 seconds.”
… which I accepted as I had the perfect recipe ...
… that often didn’t quite work as expected ...
… leading to several hard-learned lessons ...
… one of them being:
Is it easy to build a
Knowledge Graph?
A tale of two graphs
• EU’s ESCO knowledge graph:
• Released September 2017
• 12K Skill and 3K Profession interrelated concepts in 27
languages
• Built completely manually by experts in 6 years and cost
~15 million Euros
• To be updated once a year by a maintenance committee
• DBPedia knowledge graph
• First release in 2007
• Currently >17M entities in 127 languages
• Automatically extracted from Wikipedia infoboxes
• Live version and monthly releases
Why the difference?
• Types of entities: Abstract entities more difficult to define than concrete
ones (e.g. “Ontology” v.s. “The Netherlands”)
• Types of relations: Vague relations harder to define and achieve
consensus (e.g. “has essential skill” v.s. “was born in”)
• Available data sources: There are no Wikipedia-like infoboxes for
Professions and Skills that could enable automatic extraction.
• Quality requirements: ESCO wanted very high accuracy.
Knowledge Graphs and
Strategy
Strategy is about “What” rather than “How”
• What domains of knowledge we want our
Knowledge Graph to cover?
• What data we want to connect?
• What applications we want to power?
• What users we want to serve?
• What quality dimensions are important and
at what levels?
Strategy is about Choices, Dilemmas and Decisions
• Domain A or Domain B?
• Accuracy or Completeness?
• Application A or Application B?
• Data-Driven or Human-Driven?
• Democracy, Oligarchy or Dictatorship?
• Single or Multiple Truths?
Crafting a Knowledge
Graph Strategy
Know thy Goals
• What business/technical goals are you trying to
achieve via the Knowledge Graph?
• Imitate the others?
• Enhance current products/processes and get
ahead of the competition ? If so, which?
• Lay the foundations for new products/processes?
If so, which?
• Integrate dispersed data and improve their
governance?
• …
• Extract!: Entity and Relation Tagging and Disambiguation in CVs and Vacancies
• Search! and Match!: Query Understanding and Expansion, Semantic Similarity
• Jobfeed: Labour Market Analytics
Example: Products enhanced by the Textkernel Knowledge
Graph
Know thy Context
• Domain(s) and Semantics
• What elements does the Knowledge Graph need to provide
(entity types, relations, etc)?
• Is there ambiguity, vagueness, semantic drift? To what extent?
• Technology Context
• What knowledge can be automatically mined with the
technology we have?
• How fast and how accurately?
• Organizational Context
• Data, technology and products
• People, knowledge and capabilities
• Processes, practices and attitudes
• Business Context
• Business strategy and model(s)
• Clients, partners and competitors
• Trends, hypes, expectations and narratives
Use Context to make choices and break dilemmas
• If your semantics are highly vague and cause disagreements you
might need to support multiple truths.
• If the best extraction system for relation X is only 50% accurate, you
will probably need manual curation.
• If there is already a non-RDF semantics management infrastructure
in the organization, it may not worth replacing it with an RDF one!
• If product A generates more revenue than product B, you might need
to optimize the KG for A.
• If your competitor outperforms you in coverage because of more data
and better infrastructure, you might want to compete on accuracy or
some niche complex domain..
Questions to think when you return to the office
Do w w y e
bu n (or t) a
Kno d G ap ?
Do w w o t
an r u “Wha ” an
b e d e m ?
➔ High-level goals are ok but
you need concrete goals
➔ Any answer with “AI”, “Big
Data” or other buzzword
should be ignored!
➔ Semantics
➔ Data
➔ Technology
➔ Organization
➔ Business
➔ Basic philosophy and
principles
➔ Definition of success (and
failure)
➔ Decision making processes
Do w w e c l e
Con t?
Thank you!
Panos Alexopoulos
Head of Ontology
E-mail: alexopoulos@textkernel.nl
Web: http://www.panosalexopoulos.com
LinkedIn: www.linkedin.com/in/panosalexopoulos
Twitter: @PAlexop

Weitere ähnliche Inhalte

Was ist angesagt?

Machine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlow
Machine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlowMachine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlow
Machine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlow
andrejusb
 
Intro to Graphs and Neo4j
Intro to Graphs and Neo4jIntro to Graphs and Neo4j
Intro to Graphs and Neo4j
jexp
 

Was ist angesagt? (20)

Edmc use cases 2018 nyc
Edmc use cases 2018   nycEdmc use cases 2018   nyc
Edmc use cases 2018 nyc
 
How a global manufacturing company built a data science capability from scratch
How a global manufacturing company built a data science capability from scratchHow a global manufacturing company built a data science capability from scratch
How a global manufacturing company built a data science capability from scratch
 
State street edmc swaps pilot
State street edmc swaps pilotState street edmc swaps pilot
State street edmc swaps pilot
 
AI-SDV 2021: Jay ven Eman - implementation-of-new-technology-within-a-big-pha...
AI-SDV 2021: Jay ven Eman - implementation-of-new-technology-within-a-big-pha...AI-SDV 2021: Jay ven Eman - implementation-of-new-technology-within-a-big-pha...
AI-SDV 2021: Jay ven Eman - implementation-of-new-technology-within-a-big-pha...
 
Machine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlow
Machine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlowMachine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlow
Machine Learning Applied - Contextual Chatbots Coding, Oracle JET and TensorFlow
 
AI-SDV 2021: Stefan Geissler - AI support for creating and maintaining vocabu...
AI-SDV 2021: Stefan Geissler - AI support for creating and maintaining vocabu...AI-SDV 2021: Stefan Geissler - AI support for creating and maintaining vocabu...
AI-SDV 2021: Stefan Geissler - AI support for creating and maintaining vocabu...
 
5. Building the Cancer Research Data Commons with Neo4j: The Bento Framework
5. Building the Cancer Research Data Commons with Neo4j: The Bento Framework5. Building the Cancer Research Data Commons with Neo4j: The Bento Framework
5. Building the Cancer Research Data Commons with Neo4j: The Bento Framework
 
Neo4j: What's Under the Hood & How Knowing This Can Help You
Neo4j: What's Under the Hood & How Knowing This Can Help You Neo4j: What's Under the Hood & How Knowing This Can Help You
Neo4j: What's Under the Hood & How Knowing This Can Help You
 
Talk to me Goose: Going beyond your regular Chatbot
Talk to me Goose: Going beyond your regular ChatbotTalk to me Goose: Going beyond your regular Chatbot
Talk to me Goose: Going beyond your regular Chatbot
 
How LinkedIn leverages data to build scalable payments strategy
How LinkedIn leverages data to build scalable payments strategyHow LinkedIn leverages data to build scalable payments strategy
How LinkedIn leverages data to build scalable payments strategy
 
GraphTour - DXC - Digital Explorer
GraphTour - DXC - Digital ExplorerGraphTour - DXC - Digital Explorer
GraphTour - DXC - Digital Explorer
 
Neo4j: What's Under the Hood
Neo4j: What's Under the HoodNeo4j: What's Under the Hood
Neo4j: What's Under the Hood
 
Compliance made easy: Lynx webinar #1
Compliance made easy: Lynx webinar #1Compliance made easy: Lynx webinar #1
Compliance made easy: Lynx webinar #1
 
Ben Gardner | Delivering a Linked Data warehouse and integrating across the w...
Ben Gardner | Delivering a Linked Data warehouse and integrating across the w...Ben Gardner | Delivering a Linked Data warehouse and integrating across the w...
Ben Gardner | Delivering a Linked Data warehouse and integrating across the w...
 
Session 2.1 ontological representation of the telecom domain for advanced a...
Session 2.1   ontological representation of the telecom domain for advanced a...Session 2.1   ontological representation of the telecom domain for advanced a...
Session 2.1 ontological representation of the telecom domain for advanced a...
 
Graph Data Science: The Secret to Accelerating Innovation with AI/ML
Graph Data Science: The Secret to Accelerating Innovation with AI/MLGraph Data Science: The Secret to Accelerating Innovation with AI/ML
Graph Data Science: The Secret to Accelerating Innovation with AI/ML
 
W3C-XBRL International Workshop 2009
W3C-XBRL International Workshop 2009W3C-XBRL International Workshop 2009
W3C-XBRL International Workshop 2009
 
Test strategy for Conversational AI
Test strategy for Conversational AITest strategy for Conversational AI
Test strategy for Conversational AI
 
AI-SDV 2020: Using Transformer technology to build an AI based personal News ...
AI-SDV 2020: Using Transformer technology to build an AI based personal News ...AI-SDV 2020: Using Transformer technology to build an AI based personal News ...
AI-SDV 2020: Using Transformer technology to build an AI based personal News ...
 
Intro to Graphs and Neo4j
Intro to Graphs and Neo4jIntro to Graphs and Neo4j
Intro to Graphs and Neo4j
 

Ähnlich wie Crafting a Knowledge Graph Strategy - What to think about

InfoVision_PM101_RPadaki
InfoVision_PM101_RPadakiInfoVision_PM101_RPadaki
InfoVision_PM101_RPadaki
Ravi Padaki
 
Data Refinement: The missing link between data collection and decisions
Data Refinement: The missing link between data collection and decisionsData Refinement: The missing link between data collection and decisions
Data Refinement: The missing link between data collection and decisions
Vivastream
 

Ähnlich wie Crafting a Knowledge Graph Strategy - What to think about (20)

Lean Analytics: How to get more out of your data science team
Lean Analytics: How to get more out of your data science teamLean Analytics: How to get more out of your data science team
Lean Analytics: How to get more out of your data science team
 
What Managers Need to Know about Data Science
What Managers Need to Know about Data ScienceWhat Managers Need to Know about Data Science
What Managers Need to Know about Data Science
 
Crafting a Compelling Data Science Resume
Crafting a Compelling Data Science ResumeCrafting a Compelling Data Science Resume
Crafting a Compelling Data Science Resume
 
Synergis60: 6 Critical Steps to Implementing Data Managment
Synergis60: 6 Critical Steps to Implementing Data ManagmentSynergis60: 6 Critical Steps to Implementing Data Managment
Synergis60: 6 Critical Steps to Implementing Data Managment
 
Certified Data Analyst - Ain GenX (Pvt.) Ltd.-3.pdf
Certified Data Analyst - Ain GenX (Pvt.) Ltd.-3.pdfCertified Data Analyst - Ain GenX (Pvt.) Ltd.-3.pdf
Certified Data Analyst - Ain GenX (Pvt.) Ltd.-3.pdf
 
CTO School Meetup - Jan 2013 Becoming Better Technical Leader
CTO School Meetup - Jan 2013   Becoming Better Technical LeaderCTO School Meetup - Jan 2013   Becoming Better Technical Leader
CTO School Meetup - Jan 2013 Becoming Better Technical Leader
 
Be the Captain of Your Career
Be the Captain of Your Career Be the Captain of Your Career
Be the Captain of Your Career
 
Lessons after working as a data scientist for 1 year
Lessons after working as a data scientist for 1 yearLessons after working as a data scientist for 1 year
Lessons after working as a data scientist for 1 year
 
How to win StartupWeekend
How to win StartupWeekendHow to win StartupWeekend
How to win StartupWeekend
 
InfoVision_PM101_RPadaki
InfoVision_PM101_RPadakiInfoVision_PM101_RPadaki
InfoVision_PM101_RPadaki
 
DACS Presentation January 2015
DACS Presentation January 2015DACS Presentation January 2015
DACS Presentation January 2015
 
DACS Presentation January 2015
DACS Presentation January 2015 DACS Presentation January 2015
DACS Presentation January 2015
 
Are you ready for Data science? A 12 point test
Are you ready for Data science? A 12 point testAre you ready for Data science? A 12 point test
Are you ready for Data science? A 12 point test
 
Scaling Training Data for AI Applications
Scaling Training Data for AI ApplicationsScaling Training Data for AI Applications
Scaling Training Data for AI Applications
 
Data and analytic strategies for developing ethical it
Data and analytic strategies for developing ethical itData and analytic strategies for developing ethical it
Data and analytic strategies for developing ethical it
 
Data Refinement: The missing link between data collection and decisions
Data Refinement: The missing link between data collection and decisionsData Refinement: The missing link between data collection and decisions
Data Refinement: The missing link between data collection and decisions
 
1 data science with python
1 data science with python1 data science with python
1 data science with python
 
How to start your data career
How to start your data careerHow to start your data career
How to start your data career
 
Enterprise search Information
Enterprise search Information Enterprise search Information
Enterprise search Information
 
Data Solutions for Products by Leadspace Director of Analytics
Data Solutions for Products by Leadspace Director of AnalyticsData Solutions for Products by Leadspace Director of Analytics
Data Solutions for Products by Leadspace Director of Analytics
 

Mehr von Connected Data World

The years of the graph: The future of the future is here
The years of the graph: The future of the future is hereThe years of the graph: The future of the future is here
The years of the graph: The future of the future is here
Connected Data World
 
In Search of the Universal Data Model
In Search of the Universal Data ModelIn Search of the Universal Data Model
In Search of the Universal Data Model
Connected Data World
 
Graph Realities
Graph RealitiesGraph Realities
Graph Realities
Connected Data World
 
RAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needsRAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needs
Connected Data World
 
Elegant and Scalable Code Querying with Code Property Graphs
Elegant and Scalable Code Querying with Code Property GraphsElegant and Scalable Code Querying with Code Property Graphs
Elegant and Scalable Code Querying with Code Property Graphs
Connected Data World
 

Mehr von Connected Data World (20)

Systems that learn and reason | Frank Van Harmelen
Systems that learn and reason | Frank Van HarmelenSystems that learn and reason | Frank Van Harmelen
Systems that learn and reason | Frank Van Harmelen
 
Graph Abstractions Matter by Ora Lassila
Graph Abstractions Matter by Ora LassilaGraph Abstractions Matter by Ora Lassila
Graph Abstractions Matter by Ora Lassila
 
Κnowledge Architecture: Combining Strategy, Data Science and Information Arch...
Κnowledge Architecture: Combining Strategy, Data Science and Information Arch...Κnowledge Architecture: Combining Strategy, Data Science and Information Arch...
Κnowledge Architecture: Combining Strategy, Data Science and Information Arch...
 
How to get started with Graph Machine Learning
How to get started with Graph Machine LearningHow to get started with Graph Machine Learning
How to get started with Graph Machine Learning
 
Graphs in sustainable finance
Graphs in sustainable financeGraphs in sustainable finance
Graphs in sustainable finance
 
The years of the graph: The future of the future is here
The years of the graph: The future of the future is hereThe years of the graph: The future of the future is here
The years of the graph: The future of the future is here
 
From Taxonomies and Schemas to Knowledge Graphs: Parts 1 & 2
From Taxonomies and Schemas to Knowledge Graphs: Parts 1 & 2From Taxonomies and Schemas to Knowledge Graphs: Parts 1 & 2
From Taxonomies and Schemas to Knowledge Graphs: Parts 1 & 2
 
From Taxonomies and Schemas to Knowledge Graphs: Part 3
From Taxonomies and Schemas to Knowledge Graphs: Part 3From Taxonomies and Schemas to Knowledge Graphs: Part 3
From Taxonomies and Schemas to Knowledge Graphs: Part 3
 
In Search of the Universal Data Model
In Search of the Universal Data ModelIn Search of the Universal Data Model
In Search of the Universal Data Model
 
Graph in Apache Cassandra. The World’s Most Scalable Graph Database
Graph in Apache Cassandra. The World’s Most Scalable Graph DatabaseGraph in Apache Cassandra. The World’s Most Scalable Graph Database
Graph in Apache Cassandra. The World’s Most Scalable Graph Database
 
Enterprise Data Governance: Leveraging Knowledge Graph & AI in support of a d...
Enterprise Data Governance: Leveraging Knowledge Graph & AI in support of a d...Enterprise Data Governance: Leveraging Knowledge Graph & AI in support of a d...
Enterprise Data Governance: Leveraging Knowledge Graph & AI in support of a d...
 
Graph Realities
Graph RealitiesGraph Realities
Graph Realities
 
Powering Question-Driven Problem Solving to Improve the Chances of Finding Ne...
Powering Question-Driven Problem Solving to Improve the Chances of Finding Ne...Powering Question-Driven Problem Solving to Improve the Chances of Finding Ne...
Powering Question-Driven Problem Solving to Improve the Chances of Finding Ne...
 
Semantic similarity for faster Knowledge Graph delivery at scale
Semantic similarity for faster Knowledge Graph delivery at scaleSemantic similarity for faster Knowledge Graph delivery at scale
Semantic similarity for faster Knowledge Graph delivery at scale
 
Knowledge Graphs and AI to Hyper-Personalise the Fashion Retail Experience at...
Knowledge Graphs and AI to Hyper-Personalise the Fashion Retail Experience at...Knowledge Graphs and AI to Hyper-Personalise the Fashion Retail Experience at...
Knowledge Graphs and AI to Hyper-Personalise the Fashion Retail Experience at...
 
Schema, Google & The Future of the Web
Schema, Google & The Future of the WebSchema, Google & The Future of the Web
Schema, Google & The Future of the Web
 
RAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needsRAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needs
 
Elegant and Scalable Code Querying with Code Property Graphs
Elegant and Scalable Code Querying with Code Property GraphsElegant and Scalable Code Querying with Code Property Graphs
Elegant and Scalable Code Querying with Code Property Graphs
 
From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...
From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...
From Knowledge Graphs to AI-powered SEO: Using taxonomies, schemas and knowle...
 
Graph for Good: Empowering your NGO
Graph for Good: Empowering your NGOGraph for Good: Empowering your NGO
Graph for Good: Empowering your NGO
 

Kürzlich hochgeladen

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Victor Rentea
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Kürzlich hochgeladen (20)

Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 

Crafting a Knowledge Graph Strategy - What to think about

  • 1. Crafting a Knowledge Graph Strategy What to think about Panos Alexopoulos Head of Ontology
  • 2. 2.5 years ago I got a mission ... • “Good morning Mr. Alexopoulos. Your mission, should you decide to accept it, is to build an HR and Recruitment Knowledge Graph.” • “As always, should you or any member of your team be caught or killed, the company will disavow any knowledge of your actions. “ • “This tape will self-destruct in 5 seconds.”
  • 3. … which I accepted as I had the perfect recipe ...
  • 4. … that often didn’t quite work as expected ...
  • 5. … leading to several hard-learned lessons ...
  • 6. … one of them being:
  • 7. Is it easy to build a Knowledge Graph?
  • 8. A tale of two graphs • EU’s ESCO knowledge graph: • Released September 2017 • 12K Skill and 3K Profession interrelated concepts in 27 languages • Built completely manually by experts in 6 years and cost ~15 million Euros • To be updated once a year by a maintenance committee • DBPedia knowledge graph • First release in 2007 • Currently >17M entities in 127 languages • Automatically extracted from Wikipedia infoboxes • Live version and monthly releases
  • 9. Why the difference? • Types of entities: Abstract entities more difficult to define than concrete ones (e.g. “Ontology” v.s. “The Netherlands”) • Types of relations: Vague relations harder to define and achieve consensus (e.g. “has essential skill” v.s. “was born in”) • Available data sources: There are no Wikipedia-like infoboxes for Professions and Skills that could enable automatic extraction. • Quality requirements: ESCO wanted very high accuracy.
  • 11. Strategy is about “What” rather than “How” • What domains of knowledge we want our Knowledge Graph to cover? • What data we want to connect? • What applications we want to power? • What users we want to serve? • What quality dimensions are important and at what levels?
  • 12. Strategy is about Choices, Dilemmas and Decisions • Domain A or Domain B? • Accuracy or Completeness? • Application A or Application B? • Data-Driven or Human-Driven? • Democracy, Oligarchy or Dictatorship? • Single or Multiple Truths?
  • 14. Know thy Goals • What business/technical goals are you trying to achieve via the Knowledge Graph? • Imitate the others? • Enhance current products/processes and get ahead of the competition ? If so, which? • Lay the foundations for new products/processes? If so, which? • Integrate dispersed data and improve their governance? • …
  • 15. • Extract!: Entity and Relation Tagging and Disambiguation in CVs and Vacancies • Search! and Match!: Query Understanding and Expansion, Semantic Similarity • Jobfeed: Labour Market Analytics Example: Products enhanced by the Textkernel Knowledge Graph
  • 16. Know thy Context • Domain(s) and Semantics • What elements does the Knowledge Graph need to provide (entity types, relations, etc)? • Is there ambiguity, vagueness, semantic drift? To what extent? • Technology Context • What knowledge can be automatically mined with the technology we have? • How fast and how accurately? • Organizational Context • Data, technology and products • People, knowledge and capabilities • Processes, practices and attitudes • Business Context • Business strategy and model(s) • Clients, partners and competitors • Trends, hypes, expectations and narratives
  • 17. Use Context to make choices and break dilemmas • If your semantics are highly vague and cause disagreements you might need to support multiple truths. • If the best extraction system for relation X is only 50% accurate, you will probably need manual curation. • If there is already a non-RDF semantics management infrastructure in the organization, it may not worth replacing it with an RDF one! • If product A generates more revenue than product B, you might need to optimize the KG for A. • If your competitor outperforms you in coverage because of more data and better infrastructure, you might want to compete on accuracy or some niche complex domain..
  • 18. Questions to think when you return to the office Do w w y e bu n (or t) a Kno d G ap ? Do w w o t an r u “Wha ” an b e d e m ? ➔ High-level goals are ok but you need concrete goals ➔ Any answer with “AI”, “Big Data” or other buzzword should be ignored! ➔ Semantics ➔ Data ➔ Technology ➔ Organization ➔ Business ➔ Basic philosophy and principles ➔ Definition of success (and failure) ➔ Decision making processes Do w w e c l e Con t?
  • 19. Thank you! Panos Alexopoulos Head of Ontology E-mail: alexopoulos@textkernel.nl Web: http://www.panosalexopoulos.com LinkedIn: www.linkedin.com/in/panosalexopoulos Twitter: @PAlexop