SlideShare a Scribd company logo
PERSONAL KNOWLEDGE GRAPHS
Krisztian Balog
University of Stavanger

@krisztianbalog
Dagstuhl Seminar on Conversa>onal Search | Dagstuhl, Germany, November 2019
KNOWLEDGE GRAPHS ARE POWERFUL ASSETS
FOR A BROAD RANGE OF SEARCH,
RECOMMENDATION, AND MINING SCENARIOS
What is the capital of
Norway?
What is its popula>on?
KNOWLEDGE GRAPHS ARE POWERFUL ASSETS
FOR A BROAD RANGE OF SEARCH,
RECOMMENDATION, AND MINING SCENARIOS
They tend to focus on prominent, globally important en@@es
This rules out many en@@es we interact with on a daily basis!
MOTIVATIONAL SCENARIO
I would like to get some new strings
for my guitar
AIOK, would that be your electric guitar or
the acoustic one?
The electric one.
AIAlright. I can repeat your Amazon order of
3 months ago, or you can go by a music
store on Elm street on the way to your
dentist appointment this afternoon.
MOTIVATIONAL SCENARIO #2
AISince you're running a half marathon at
Hackney in May, may I suggest you
undertake a 10k run this weekend?
Yes, that sounds like a good idea. Any
suggestions for a not too popular route 

that I haven't done before?
AISure thing. I'll upload some routes to the
running app on your phone.
Cheers mate!
IT IS DIFFICULT TO IMAGINE A TRULY
PERSONAL CONVERSATIONAL ASSISTANT
WITHOUT IT HAVING ACCESS TO
STRUCTURED PERSONAL INFORMATION
PERSONAL KNOWLEDGE GRAPHS
A personal knowledge graph (PKG) is
a resource of structured information
about entities that are of personal
interest to the user
Key differences from general KGs:
• Entities of personal interest to the user
• Distinctive shape (“spiderweb” layout)
• Links between a PKG and external
sources are inherent to its nature
ASSOCIATED PROBLEMS
• Knowledge representation
• Semantic annotation of text
• Population and maintenance
• Integration with external sources
KNOWLEDGE REPRESENTATION
Task: representing entities and their properties
• KGs are organized according to a knowledge model (schema)
Peculiarities/challenges
• Entities need to be (directly/indirectly) connected to the user
• Not all attributes have to be filled; the focus is on personal relevance
• Information about entities can be very sparse
• Some entities may not have any digital presence
• Relations can be highly temporal in nature
RQ1
How should en@@es and their proper@es and rela@ons be represented,
considering the vast but sparse set of possible predicates and their short-lived
nature?
SEMANTIC ANNOTATION OF TEXT
Task: annotating text with respect to a knowledge repository (commonly
known as entity linking)
• Usually involves mention detection, entity disambiguation, and NIL-
detection
Challenges
• Entities might have little to no digital presence
• Entities are not necessarily proper nouns
• Linking, NIL-detection, and KG population are intertwined
RQ2a How can en@ty linking be performed against a personal knowledge graph,
where structured en@ty informa@on to rely on is poten@ally absent?
When should en@ty linking be performed against a personal knowledge graph
as opposed to a general-purpose KG?
RQ2b
POPULATION AND MAINTENANCE
Task: extending a KG from external sources (KB acceleration/
population) or via internal inferencing
• Verification of facts in the KG
Challenges
• Single curator => More automation is desired than for KGs, but the
user should still be in control
• The first mention of an entity should trigger population
• Properties may be inferred from the context
RQ3 How can personal knowledge graphs be automa@cally populated and reliably
maintained?
INTEGRATION WITH EXTERNAL SOURCES
Task: recognizing the same entity across multiple data sources
• Also known as: object resolution, record linkage
Challenges
• One-to-many, as opposed to one-to-one linkage
• Continuous process, not a one-off effort
• Two-way synchronization would be desired
• Conflicting facts or relations need resolving by the user
RQ4 How should external knowledge sources con@nuously be integrated with, in a
two-way process, poten@ally involving the user?
THERE IS MORE…
Evaluation
• This would require an environment where users can interact with a
PKG
Implementation
• Storage (cloud vs. device), security, privacy, access control, ...
Utilization
• From specific apps (calendar, health/wellbeing app, etc.) to a truly
personal assistant
TAKING CONTROL OF OUR DATA
Present Alternative
service #1
service #2
service #3
service #1
service #2
service #3
Different service providers each have some (possibly
overlapping) portion of the person’s PKG
The person has full control over her PKG and may grant access
to different service providers to specific parts of the PKG
http://bit.ly/ictir2019-pkg

More Related Content

What's hot

SDA 1982-1995 - Infiltration
SDA 1982-1995 - InfiltrationSDA 1982-1995 - Infiltration
SDA 1982-1995 - Infiltration
Sami Wilberforce
 
Journey through the Sundays of Lent
Journey through the Sundays of LentJourney through the Sundays of Lent
Journey through the Sundays of Lent
Ehab Roufail
 
The Adamic Covenant
The Adamic CovenantThe Adamic Covenant
The Adamic Covenant
Learning to Prophesy
 
Joyful mysteries of rosary
Joyful mysteries of rosaryJoyful mysteries of rosary
Joyful mysteries of rosary
Andy cronico
 
Repentance Lesson Four
Repentance Lesson FourRepentance Lesson Four
Repentance Lesson Four
ACTS238 Believer
 
Genesis 15 17: The Abrahamic covenant
Genesis 15 17: The Abrahamic covenantGenesis 15 17: The Abrahamic covenant
Genesis 15 17: The Abrahamic covenant
DrPothana
 
Tunay na pagsisisi
Tunay na pagsisisiTunay na pagsisisi
Tunay na pagsisisi
Maria Teresa Gimeno
 
Genesis Creation
Genesis CreationGenesis Creation
Genesis Creation
rfjohnson
 
Edu.03 assignment
Edu.03 assignment Edu.03 assignment
Edu.03 assignment
LudiyaStanlySG
 
Communion
CommunionCommunion
Communion
Mary Sorial
 
Failures!
Failures!Failures!
Skillshare - Introduction to Data Scraping
Skillshare - Introduction to Data ScrapingSkillshare - Introduction to Data Scraping
Skillshare - Introduction to Data Scraping
School of Data
 
Sorrowful Mysteries of the Rosary Novena
Sorrowful Mysteries of the Rosary NovenaSorrowful Mysteries of the Rosary Novena
Sorrowful Mysteries of the Rosary Novena
Rose Vinh-Morton
 
Angelus tagalog
Angelus tagalogAngelus tagalog
Angelus tagalogSirGie To
 
Rise of the Antichrist
Rise of the AntichristRise of the Antichrist
Ir models
Ir modelsIr models
Ir models
Ambreen Angel
 
Eschatology: Lecture-8
Eschatology: Lecture-8Eschatology: Lecture-8
Eschatology: Lecture-8
COACH International Ministries
 
Stay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible Study
Stay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible StudyStay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible Study
Stay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible Study
Danny Scotton, Jr.
 
05 the-holy-spirit
05 the-holy-spirit05 the-holy-spirit
05 the-holy-spirit
Tyrone Palm
 
Shadows in the Tabernacle - the priesthood old and new
Shadows in the Tabernacle - the priesthood old and newShadows in the Tabernacle - the priesthood old and new
Shadows in the Tabernacle - the priesthood old and new
Alan Williamson
 

What's hot (20)

SDA 1982-1995 - Infiltration
SDA 1982-1995 - InfiltrationSDA 1982-1995 - Infiltration
SDA 1982-1995 - Infiltration
 
Journey through the Sundays of Lent
Journey through the Sundays of LentJourney through the Sundays of Lent
Journey through the Sundays of Lent
 
The Adamic Covenant
The Adamic CovenantThe Adamic Covenant
The Adamic Covenant
 
Joyful mysteries of rosary
Joyful mysteries of rosaryJoyful mysteries of rosary
Joyful mysteries of rosary
 
Repentance Lesson Four
Repentance Lesson FourRepentance Lesson Four
Repentance Lesson Four
 
Genesis 15 17: The Abrahamic covenant
Genesis 15 17: The Abrahamic covenantGenesis 15 17: The Abrahamic covenant
Genesis 15 17: The Abrahamic covenant
 
Tunay na pagsisisi
Tunay na pagsisisiTunay na pagsisisi
Tunay na pagsisisi
 
Genesis Creation
Genesis CreationGenesis Creation
Genesis Creation
 
Edu.03 assignment
Edu.03 assignment Edu.03 assignment
Edu.03 assignment
 
Communion
CommunionCommunion
Communion
 
Failures!
Failures!Failures!
Failures!
 
Skillshare - Introduction to Data Scraping
Skillshare - Introduction to Data ScrapingSkillshare - Introduction to Data Scraping
Skillshare - Introduction to Data Scraping
 
Sorrowful Mysteries of the Rosary Novena
Sorrowful Mysteries of the Rosary NovenaSorrowful Mysteries of the Rosary Novena
Sorrowful Mysteries of the Rosary Novena
 
Angelus tagalog
Angelus tagalogAngelus tagalog
Angelus tagalog
 
Rise of the Antichrist
Rise of the AntichristRise of the Antichrist
Rise of the Antichrist
 
Ir models
Ir modelsIr models
Ir models
 
Eschatology: Lecture-8
Eschatology: Lecture-8Eschatology: Lecture-8
Eschatology: Lecture-8
 
Stay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible Study
Stay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible StudyStay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible Study
Stay Woke: Be Ready and Steady! | 1 Thessalonians 5:1-11 Bible Study
 
05 the-holy-spirit
05 the-holy-spirit05 the-holy-spirit
05 the-holy-spirit
 
Shadows in the Tabernacle - the priesthood old and new
Shadows in the Tabernacle - the priesthood old and newShadows in the Tabernacle - the priesthood old and new
Shadows in the Tabernacle - the priesthood old and new
 

Similar to Personal Knowledge Graphs

On Entities and Evaluation
On Entities and EvaluationOn Entities and Evaluation
On Entities and Evaluation
krisztianbalog
 
Odsc 2019 entity_reputation_knowledge_graph
Odsc 2019 entity_reputation_knowledge_graphOdsc 2019 entity_reputation_knowledge_graph
Odsc 2019 entity_reputation_knowledge_graph
venkatramanJ4
 
Serendipity
SerendipitySerendipity
Serendipity
hashbo
 
Serendipity-neo4j
Serendipity-neo4jSerendipity-neo4j
Serendipity-neo4j
Skills Matter
 
Applications for Social Networking Strategies in an Agency Context
Applications for Social Networking Strategies in an Agency ContextApplications for Social Networking Strategies in an Agency Context
Applications for Social Networking Strategies in an Agency Context
John Brisbin
 
Applications for Social Networking Strategies in an Agency Context: Exploitin...
Applications for Social Networking Strategies in an Agency Context: Exploitin...Applications for Social Networking Strategies in an Agency Context: Exploitin...
Applications for Social Networking Strategies in an Agency Context: Exploitin...
BoaB Team
 
Open IE tutorial 2018
Open IE tutorial 2018Open IE tutorial 2018
Open IE tutorial 2018
Andre Freitas
 
AI Beyond Deep Learning
AI Beyond Deep LearningAI Beyond Deep Learning
AI Beyond Deep Learning
Andre Freitas
 
SCRY @ ISWC'15, Diversity++
SCRY @ ISWC'15, Diversity++SCRY @ ISWC'15, Diversity++
SCRY @ ISWC'15, Diversity++
Bas Stringer
 
Resource Description Pres and Paper
Resource Description Pres and PaperResource Description Pres and Paper
Resource Description Pres and Paper
National Library of Australia
 
Deduplication and Author-Disambiguation of Streaming Records via Supervised M...
Deduplication and Author-Disambiguation of Streaming Records via Supervised M...Deduplication and Author-Disambiguation of Streaming Records via Supervised M...
Deduplication and Author-Disambiguation of Streaming Records via Supervised M...
Spark Summit
 
Cataloging Presentation
Cataloging PresentationCataloging Presentation
Cataloging Presentation
Angela Dresselhaus
 
Authority of assertion in repository contributions to the PID graph / George ...
Authority of assertion in repository contributions to the PID graph / George ...Authority of assertion in repository contributions to the PID graph / George ...
Authority of assertion in repository contributions to the PID graph / George ...
CILIP MDG
 
An Introduction to NOSQL, Graph Databases and Neo4j
An Introduction to NOSQL, Graph Databases and Neo4jAn Introduction to NOSQL, Graph Databases and Neo4j
An Introduction to NOSQL, Graph Databases and Neo4j
Debanjan Mahata
 
Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...
Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...
Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...
Databricks
 
Ngsp
NgspNgsp
Ngsp
Tim Clark
 
Human Machine Collaboration for Improved Analytical Processes
Human Machine Collaboration for Improved Analytical ProcessesHuman Machine Collaboration for Improved Analytical Processes
Human Machine Collaboration for Improved Analytical Processes
Tony Ojeda
 
What Is GDS and Neo4j’s GDS Library
What Is GDS and Neo4j’s GDS LibraryWhat Is GDS and Neo4j’s GDS Library
What Is GDS and Neo4j’s GDS Library
Neo4j
 
Data Communities - reusable data in and outside your organization.
Data Communities - reusable data in and outside your organization.Data Communities - reusable data in and outside your organization.
Data Communities - reusable data in and outside your organization.
Paul Groth
 
Managing 'Big Data' in the social sciences: the contribution of an analytico-...
Managing 'Big Data' in the social sciences: the contribution of an analytico-...Managing 'Big Data' in the social sciences: the contribution of an analytico-...
Managing 'Big Data' in the social sciences: the contribution of an analytico-...
CILIP MDG
 

Similar to Personal Knowledge Graphs (20)

On Entities and Evaluation
On Entities and EvaluationOn Entities and Evaluation
On Entities and Evaluation
 
Odsc 2019 entity_reputation_knowledge_graph
Odsc 2019 entity_reputation_knowledge_graphOdsc 2019 entity_reputation_knowledge_graph
Odsc 2019 entity_reputation_knowledge_graph
 
Serendipity
SerendipitySerendipity
Serendipity
 
Serendipity-neo4j
Serendipity-neo4jSerendipity-neo4j
Serendipity-neo4j
 
Applications for Social Networking Strategies in an Agency Context
Applications for Social Networking Strategies in an Agency ContextApplications for Social Networking Strategies in an Agency Context
Applications for Social Networking Strategies in an Agency Context
 
Applications for Social Networking Strategies in an Agency Context: Exploitin...
Applications for Social Networking Strategies in an Agency Context: Exploitin...Applications for Social Networking Strategies in an Agency Context: Exploitin...
Applications for Social Networking Strategies in an Agency Context: Exploitin...
 
Open IE tutorial 2018
Open IE tutorial 2018Open IE tutorial 2018
Open IE tutorial 2018
 
AI Beyond Deep Learning
AI Beyond Deep LearningAI Beyond Deep Learning
AI Beyond Deep Learning
 
SCRY @ ISWC'15, Diversity++
SCRY @ ISWC'15, Diversity++SCRY @ ISWC'15, Diversity++
SCRY @ ISWC'15, Diversity++
 
Resource Description Pres and Paper
Resource Description Pres and PaperResource Description Pres and Paper
Resource Description Pres and Paper
 
Deduplication and Author-Disambiguation of Streaming Records via Supervised M...
Deduplication and Author-Disambiguation of Streaming Records via Supervised M...Deduplication and Author-Disambiguation of Streaming Records via Supervised M...
Deduplication and Author-Disambiguation of Streaming Records via Supervised M...
 
Cataloging Presentation
Cataloging PresentationCataloging Presentation
Cataloging Presentation
 
Authority of assertion in repository contributions to the PID graph / George ...
Authority of assertion in repository contributions to the PID graph / George ...Authority of assertion in repository contributions to the PID graph / George ...
Authority of assertion in repository contributions to the PID graph / George ...
 
An Introduction to NOSQL, Graph Databases and Neo4j
An Introduction to NOSQL, Graph Databases and Neo4jAn Introduction to NOSQL, Graph Databases and Neo4j
An Introduction to NOSQL, Graph Databases and Neo4j
 
Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...
Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...
Building a Knowledge Graph with Spark and NLP: How We Recommend Novel Drugs t...
 
Ngsp
NgspNgsp
Ngsp
 
Human Machine Collaboration for Improved Analytical Processes
Human Machine Collaboration for Improved Analytical ProcessesHuman Machine Collaboration for Improved Analytical Processes
Human Machine Collaboration for Improved Analytical Processes
 
What Is GDS and Neo4j’s GDS Library
What Is GDS and Neo4j’s GDS LibraryWhat Is GDS and Neo4j’s GDS Library
What Is GDS and Neo4j’s GDS Library
 
Data Communities - reusable data in and outside your organization.
Data Communities - reusable data in and outside your organization.Data Communities - reusable data in and outside your organization.
Data Communities - reusable data in and outside your organization.
 
Managing 'Big Data' in the social sciences: the contribution of an analytico-...
Managing 'Big Data' in the social sciences: the contribution of an analytico-...Managing 'Big Data' in the social sciences: the contribution of an analytico-...
Managing 'Big Data' in the social sciences: the contribution of an analytico-...
 

More from krisztianbalog

Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
krisztianbalog
 
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
krisztianbalog
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
krisztianbalog
 
Entities for Augmented Intelligence
Entities for Augmented IntelligenceEntities for Augmented Intelligence
Entities for Augmented Intelligence
krisztianbalog
 
Table Retrieval and Generation
Table Retrieval and GenerationTable Retrieval and Generation
Table Retrieval and Generation
krisztianbalog
 
Entity Search: The Last Decade and the Next
Entity Search: The Last Decade and the NextEntity Search: The Last Decade and the Next
Entity Search: The Last Decade and the Next
krisztianbalog
 
Overview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search EditionOverview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search Edition
krisztianbalog
 
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF LabOverview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
krisztianbalog
 
Entity Linking
Entity LinkingEntity Linking
Entity Linking
krisztianbalog
 
Evaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented SearchEvaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented Search
krisztianbalog
 
Entity Retrieval (tutorial organized by Radialpoint in Montreal)
Entity Retrieval (tutorial organized by Radialpoint in Montreal)Entity Retrieval (tutorial organized by Radialpoint in Montreal)
Entity Retrieval (tutorial organized by Radialpoint in Montreal)
krisztianbalog
 
Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)
krisztianbalog
 
Time-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation SystemsTime-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation Systems
krisztianbalog
 
Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)
krisztianbalog
 
Multi-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation RecommendationMulti-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation Recommendation
krisztianbalog
 
Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)
krisztianbalog
 
Semistructured Data Seach
Semistructured Data SeachSemistructured Data Seach
Semistructured Data Seach
krisztianbalog
 
Collection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity SearchCollection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity Search
krisztianbalog
 

More from krisztianbalog (18)

Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
Towards Filling the Gap in Conversational Search: From Passage Retrieval to C...
 
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...Conversational AI from an Information Retrieval Perspective: Remaining Challe...
Conversational AI from an Information Retrieval Perspective: Remaining Challe...
 
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?What Does Conversational Information Access Exactly Mean and How to Evaluate It?
What Does Conversational Information Access Exactly Mean and How to Evaluate It?
 
Entities for Augmented Intelligence
Entities for Augmented IntelligenceEntities for Augmented Intelligence
Entities for Augmented Intelligence
 
Table Retrieval and Generation
Table Retrieval and GenerationTable Retrieval and Generation
Table Retrieval and Generation
 
Entity Search: The Last Decade and the Next
Entity Search: The Last Decade and the NextEntity Search: The Last Decade and the Next
Entity Search: The Last Decade and the Next
 
Overview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search EditionOverview of the TREC 2016 Open Search track: Academic Search Edition
Overview of the TREC 2016 Open Search track: Academic Search Edition
 
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF LabOverview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
Overview of the Living Labs for IR Evaluation (LL4IR) CLEF Lab
 
Entity Linking
Entity LinkingEntity Linking
Entity Linking
 
Evaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented SearchEvaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented Search
 
Entity Retrieval (tutorial organized by Radialpoint in Montreal)
Entity Retrieval (tutorial organized by Radialpoint in Montreal)Entity Retrieval (tutorial organized by Radialpoint in Montreal)
Entity Retrieval (tutorial organized by Radialpoint in Montreal)
 
Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)Entity Retrieval (WSDM 2014 tutorial)
Entity Retrieval (WSDM 2014 tutorial)
 
Time-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation SystemsTime-aware Evaluation of Cumulative Citation Recommendation Systems
Time-aware Evaluation of Cumulative Citation Recommendation Systems
 
Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)Entity Retrieval (SIGIR 2013 tutorial)
Entity Retrieval (SIGIR 2013 tutorial)
 
Multi-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation RecommendationMulti-step Classification Approaches to Cumulative Citation Recommendation
Multi-step Classification Approaches to Cumulative Citation Recommendation
 
Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)Entity Retrieval (WWW 2013 tutorial)
Entity Retrieval (WWW 2013 tutorial)
 
Semistructured Data Seach
Semistructured Data SeachSemistructured Data Seach
Semistructured Data Seach
 
Collection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity SearchCollection Ranking and Selection for Federated Entity Search
Collection Ranking and Selection for Federated Entity Search
 

Recently uploaded

HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
panagenda
 
“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”
Claudio Di Ciccio
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
DianaGray10
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
kumardaparthi1024
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
Adtran
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
panagenda
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
DianaGray10
 
Full-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalizationFull-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalization
Zilliz
 
How to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For FlutterHow to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For Flutter
Daiki Mogmet Ito
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
Tomaz Bratanic
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
shyamraj55
 
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdfUni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems S.M.S.A.
 
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
Edge AI and Vision Alliance
 
Mariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceXMariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceX
Mariano Tinti
 
Infrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI modelsInfrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI models
Zilliz
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
Neo4j
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 

Recently uploaded (20)

HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
 
“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”“I’m still / I’m still / Chaining from the Block”
“I’m still / I’m still / Chaining from the Block”
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
GenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizationsGenAI Pilot Implementation in the organizations
GenAI Pilot Implementation in the organizations
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
 
Full-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalizationFull-RAG: A modern architecture for hyper-personalization
Full-RAG: A modern architecture for hyper-personalization
 
How to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For FlutterHow to use Firebase Data Connect For Flutter
How to use Firebase Data Connect For Flutter
 
GraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracyGraphRAG for Life Science to increase LLM accuracy
GraphRAG for Life Science to increase LLM accuracy
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
 
Uni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdfUni Systems Copilot event_05062024_C.Vlachos.pdf
Uni Systems Copilot event_05062024_C.Vlachos.pdf
 
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
“Building and Scaling AI Applications with the Nx AI Manager,” a Presentation...
 
Mariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceXMariano G Tinti - Decoding SpaceX
Mariano G Tinti - Decoding SpaceX
 
Infrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI modelsInfrastructure Challenges in Scaling RAG with Custom AI models
Infrastructure Challenges in Scaling RAG with Custom AI models
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 

Personal Knowledge Graphs

  • 1. PERSONAL KNOWLEDGE GRAPHS Krisztian Balog University of Stavanger
 @krisztianbalog Dagstuhl Seminar on Conversa>onal Search | Dagstuhl, Germany, November 2019
  • 2. KNOWLEDGE GRAPHS ARE POWERFUL ASSETS FOR A BROAD RANGE OF SEARCH, RECOMMENDATION, AND MINING SCENARIOS
  • 3.
  • 4. What is the capital of Norway?
  • 5. What is its popula>on?
  • 6. KNOWLEDGE GRAPHS ARE POWERFUL ASSETS FOR A BROAD RANGE OF SEARCH, RECOMMENDATION, AND MINING SCENARIOS They tend to focus on prominent, globally important en@@es This rules out many en@@es we interact with on a daily basis!
  • 7. MOTIVATIONAL SCENARIO I would like to get some new strings for my guitar AIOK, would that be your electric guitar or the acoustic one? The electric one. AIAlright. I can repeat your Amazon order of 3 months ago, or you can go by a music store on Elm street on the way to your dentist appointment this afternoon.
  • 8. MOTIVATIONAL SCENARIO #2 AISince you're running a half marathon at Hackney in May, may I suggest you undertake a 10k run this weekend? Yes, that sounds like a good idea. Any suggestions for a not too popular route 
 that I haven't done before? AISure thing. I'll upload some routes to the running app on your phone. Cheers mate!
  • 9. IT IS DIFFICULT TO IMAGINE A TRULY PERSONAL CONVERSATIONAL ASSISTANT WITHOUT IT HAVING ACCESS TO STRUCTURED PERSONAL INFORMATION
  • 10. PERSONAL KNOWLEDGE GRAPHS A personal knowledge graph (PKG) is a resource of structured information about entities that are of personal interest to the user Key differences from general KGs: • Entities of personal interest to the user • Distinctive shape (“spiderweb” layout) • Links between a PKG and external sources are inherent to its nature
  • 11. ASSOCIATED PROBLEMS • Knowledge representation • Semantic annotation of text • Population and maintenance • Integration with external sources
  • 12. KNOWLEDGE REPRESENTATION Task: representing entities and their properties • KGs are organized according to a knowledge model (schema) Peculiarities/challenges • Entities need to be (directly/indirectly) connected to the user • Not all attributes have to be filled; the focus is on personal relevance • Information about entities can be very sparse • Some entities may not have any digital presence • Relations can be highly temporal in nature RQ1 How should en@@es and their proper@es and rela@ons be represented, considering the vast but sparse set of possible predicates and their short-lived nature?
  • 13. SEMANTIC ANNOTATION OF TEXT Task: annotating text with respect to a knowledge repository (commonly known as entity linking) • Usually involves mention detection, entity disambiguation, and NIL- detection Challenges • Entities might have little to no digital presence • Entities are not necessarily proper nouns • Linking, NIL-detection, and KG population are intertwined RQ2a How can en@ty linking be performed against a personal knowledge graph, where structured en@ty informa@on to rely on is poten@ally absent? When should en@ty linking be performed against a personal knowledge graph as opposed to a general-purpose KG? RQ2b
  • 14. POPULATION AND MAINTENANCE Task: extending a KG from external sources (KB acceleration/ population) or via internal inferencing • Verification of facts in the KG Challenges • Single curator => More automation is desired than for KGs, but the user should still be in control • The first mention of an entity should trigger population • Properties may be inferred from the context RQ3 How can personal knowledge graphs be automa@cally populated and reliably maintained?
  • 15. INTEGRATION WITH EXTERNAL SOURCES Task: recognizing the same entity across multiple data sources • Also known as: object resolution, record linkage Challenges • One-to-many, as opposed to one-to-one linkage • Continuous process, not a one-off effort • Two-way synchronization would be desired • Conflicting facts or relations need resolving by the user RQ4 How should external knowledge sources con@nuously be integrated with, in a two-way process, poten@ally involving the user?
  • 16. THERE IS MORE… Evaluation • This would require an environment where users can interact with a PKG Implementation • Storage (cloud vs. device), security, privacy, access control, ... Utilization • From specific apps (calendar, health/wellbeing app, etc.) to a truly personal assistant
  • 17. TAKING CONTROL OF OUR DATA Present Alternative service #1 service #2 service #3 service #1 service #2 service #3 Different service providers each have some (possibly overlapping) portion of the person’s PKG The person has full control over her PKG and may grant access to different service providers to specific parts of the PKG