SlideShare a Scribd company logo
1 of 14
Download to read offline
Handling Dynamicity and Temporality of
Web Data
Hady Elsahar
hadyelsahar@gmail.com
Jean Monnet University
Saint-Étienne, France
First try with Question Answering
Weet it : Natural language interface for Linked Data (ElSahar et al. ‘11 )
● Most of the current knowledge bases focus on static facts and ignore
the temporal dimension of facts.
● Aspects of temporality and Dynamicity of Datasets :
○ Aspect 1 : Many facts are valid only during a particular time period.
○ Aspect 2 : New extracted facts can contradict with, verify or modify new ones
○ Aspect 3 : Some Facts are collectively induced from a series of Events
Handling Dynamicity of Data
Challenges and Motivations (1) :
Stephen Hawking
Many facts are valid only during a particular time
period.
Use Case : Questions about Temporal facts
● Who is first Wife of Stephen Hawiking ?
● Who is the 10th President of France ?
● Who is the past CEO of google ?
Extraction and Represenation of Temporal data
Extraction and representation of Temporal Facts and Events
❏ Representation :
❏ Keeping the last updated fact is not enough (DBpedia)
❏ Higher order fact (Erdal and Weikum ‘11)
❏ f1:Bill_Clinton isPresidentOf USA.
❏ f2:f1 startedOnDate 20-01-1993
❏ Wikidata Qualifiers (Vrandečić ‘12)
❏ Temporal fact and event extraction:
❏ Free Text and structured data from wikipedia (patterns and pattern induction)
(Erdal and Weikum ‘11)
Annotation of temporal facts in documents for Question answering
SemEval-2015 Task 5: QA TempEval
SemEval-2015 Task 5: QA TempEval
Question Examples in the Evaluation Dataset :
Yes / No:
● “Did the the Indonesian stock market rise again after it’s last fall ?
List:
● “What happened after the crash?”
● “What happened between the crash and yesterday?”
When (Factoid):
● “When did the Oscar ceremony end yesterday ?”
Applications ?
Challenges and Motivations (2) :
Stephen Hawking
In Highly dynamic datasets, new extracted facts
can contradict with, verify or modify new ones.
Existing facts New Extracted Fact
Matt Smith
is dbo:starring of
■ dbr:Womb_(film)
■ dbr:Lost_River_(film)
■ dbr:Bert_and_Dickie
■ dbr:The_Science_of_Doctor_Who
“Matt Smith is the doctor”
(Matt Smith, occupation, Medicine)
confidence : 0.1
(Frank Sinatra, profession, Singer) confidence : 0.9
(Jared leto, influenced_by, Frank Sinatra) confidence : 0.8
● People influenced by Writers are probably writers as well
● people are probably born at the same place of their siblings
Challenges and Motivations (2) :
Stephen Hawking
In Highly dynamic datasets, new extracted facts
can contradict with, verify or modify new ones.
Evaluation of new facts using Link prediction
Link Prediction
● Add new facts without extra knowledge
● Assess the validity of an unknown fact
Embedding Models for knowledge bases
TransE : Modeling Relations as Translations (Bordes et al. ’13):
● Modeling Facts as translations between vectors of entities
VSubject
+ VRelation
≅ VObject
● distance is used to Quantify confidence in facts
● Training objective: Find the representations that Minimizes distances across all true facts and
maximize across “corrupted” facts ( s’ , o’ ):
Other Embedding Models:
● Structured Embeddings (SE) (Bordes et al ‘11 )
● Collective Matrix Factorization (RESCAL) (Nickel et al., ’11)
● Neural Tensor Networks (socher et al. ‘13)
● TATEC (Garcia-Duran et al., ’14)
Embedding Models for Text + Knowledge bases:
● Joint Learning of Words and Meaning Representations (Bordes et al. ‘12)
● Knowledge Graph and Text Jointly Embedding (Wang et al ‘14)
Link prediction using Embedding Models
Applications ?
● Verification of new Extracted Facts
● Completeness of new added datasets
● Modeing literals dataypes (length, date ..etc ) not only relations and
entities.
Embedding Models other benefits ? (collaboration potential)
● Entity Disambiguation for Fact Extraction and QA (Bordes et al. ‘12)
● Paraphrase Detection for Questions, (PARALEX) (Fader et al. ‘13)
Challenges and Motivations (3) :
Reasoning with more than one supporting
facts ● Reasoning about positions (ex: Geo Data)
● Reasoning about Counts
● Reasoning about sizesFact 1 : 55 passengers crammed into the smuggler’s boat.
Fact 2 : The boat made it to the Greek island.
Question : Where are the passengers ?
Stephen Hawking
Facts induced from a series of Events
● Towards AI-Complete QA: A Set of Prerequisite Toy Tasks (Wetson et al ‘15)
● Memory Networks (Wetson et al ‘14)

More Related Content

Viewers also liked

Smart Comm Marketing Report
Smart Comm Marketing ReportSmart Comm Marketing Report
Smart Comm Marketing ReportBrian DeMontfort
 
Starting a portfolio
Starting a portfolioStarting a portfolio
Starting a portfolioMaven
 
Clipping El Observador Solitario 14/11/11 @ IED Barcelona
Clipping El Observador Solitario 14/11/11 @ IED BarcelonaClipping El Observador Solitario 14/11/11 @ IED Barcelona
Clipping El Observador Solitario 14/11/11 @ IED BarcelonaIED Barcelona
 
Clipping Hola.com 14/11/11 @ IED Barcelona
Clipping Hola.com 14/11/11 @ IED BarcelonaClipping Hola.com 14/11/11 @ IED Barcelona
Clipping Hola.com 14/11/11 @ IED BarcelonaIED Barcelona
 
120313 wb mpresentation_rotterdam2012
120313 wb mpresentation_rotterdam2012120313 wb mpresentation_rotterdam2012
120313 wb mpresentation_rotterdam2012ralphbrieskorn
 
Understanding project management qualifications
Understanding project management qualificationsUnderstanding project management qualifications
Understanding project management qualificationsMaven
 
Data center dynamics ver. 1.0
Data center dynamics ver. 1.0Data center dynamics ver. 1.0
Data center dynamics ver. 1.0Hajime Arimoto
 
SES - Plush Search
SES - Plush SearchSES - Plush Search
SES - Plush SearchPhilip James
 
Trabajo investigación udh 2015
Trabajo investigación udh 2015Trabajo investigación udh 2015
Trabajo investigación udh 2015oscar rivera
 
. Net Training Institute in Noida/NCR
. Net Training Institute in Noida/NCR. Net Training Institute in Noida/NCR
. Net Training Institute in Noida/NCRTech Mentro
 
Perfil Profesional J.Carlos Nesta
Perfil Profesional J.Carlos NestaPerfil Profesional J.Carlos Nesta
Perfil Profesional J.Carlos NestaJ. Carlos Nesta
 

Viewers also liked (20)

Smart Comm Marketing Report
Smart Comm Marketing ReportSmart Comm Marketing Report
Smart Comm Marketing Report
 
Starting a portfolio
Starting a portfolioStarting a portfolio
Starting a portfolio
 
AFMS April 2014 - Louisiana Resources & Issues
AFMS April 2014 - Louisiana Resources & IssuesAFMS April 2014 - Louisiana Resources & Issues
AFMS April 2014 - Louisiana Resources & Issues
 
Clipping El Observador Solitario 14/11/11 @ IED Barcelona
Clipping El Observador Solitario 14/11/11 @ IED BarcelonaClipping El Observador Solitario 14/11/11 @ IED Barcelona
Clipping El Observador Solitario 14/11/11 @ IED Barcelona
 
Frase maleïda
Frase maleïdaFrase maleïda
Frase maleïda
 
Clipping Hola.com 14/11/11 @ IED Barcelona
Clipping Hola.com 14/11/11 @ IED BarcelonaClipping Hola.com 14/11/11 @ IED Barcelona
Clipping Hola.com 14/11/11 @ IED Barcelona
 
120313 wb mpresentation_rotterdam2012
120313 wb mpresentation_rotterdam2012120313 wb mpresentation_rotterdam2012
120313 wb mpresentation_rotterdam2012
 
Understanding project management qualifications
Understanding project management qualificationsUnderstanding project management qualifications
Understanding project management qualifications
 
Data center dynamics ver. 1.0
Data center dynamics ver. 1.0Data center dynamics ver. 1.0
Data center dynamics ver. 1.0
 
STC PMC Newsletter 2011-04
STC PMC Newsletter 2011-04STC PMC Newsletter 2011-04
STC PMC Newsletter 2011-04
 
SES - Plush Search
SES - Plush SearchSES - Plush Search
SES - Plush Search
 
Ds 011 201100000002
Ds 011 201100000002Ds 011 201100000002
Ds 011 201100000002
 
Trabajo investigación udh 2015
Trabajo investigación udh 2015Trabajo investigación udh 2015
Trabajo investigación udh 2015
 
All about
All aboutAll about
All about
 
Synthetic division
Synthetic divisionSynthetic division
Synthetic division
 
. Net Training Institute in Noida/NCR
. Net Training Institute in Noida/NCR. Net Training Institute in Noida/NCR
. Net Training Institute in Noida/NCR
 
LOGA State of the Industry: Houston, TX
LOGA State of the Industry: Houston, TXLOGA State of the Industry: Houston, TX
LOGA State of the Industry: Houston, TX
 
Perfil Profesional J.Carlos Nesta
Perfil Profesional J.Carlos NestaPerfil Profesional J.Carlos Nesta
Perfil Profesional J.Carlos Nesta
 
Currency book
Currency bookCurrency book
Currency book
 
INGLES V
INGLES VINGLES V
INGLES V
 

Similar to WDAqua introduction presentation

From Web Data to Knowledge: on the Complementarity of Human and Artificial In...
From Web Data to Knowledge: on the Complementarity of Human and Artificial In...From Web Data to Knowledge: on the Complementarity of Human and Artificial In...
From Web Data to Knowledge: on the Complementarity of Human and Artificial In...Stefan Dietze
 
Big Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&DBig Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&DUniversity of Washington
 
Broad Data (India 2015)
Broad Data (India 2015)Broad Data (India 2015)
Broad Data (India 2015)James Hendler
 
Session 01 designing and scoping a data science project
Session 01 designing and scoping a data science projectSession 01 designing and scoping a data science project
Session 01 designing and scoping a data science projectbodaceacat
 
Session 01 designing and scoping a data science project
Session 01 designing and scoping a data science projectSession 01 designing and scoping a data science project
Session 01 designing and scoping a data science projectSara-Jayne Terp
 
Mapping (big) data science (15 dec2014)대학(원)생
Mapping (big) data science (15 dec2014)대학(원)생Mapping (big) data science (15 dec2014)대학(원)생
Mapping (big) data science (15 dec2014)대학(원)생Han Woo PARK
 
Kdd 2014 tutorial bringing structure to text - chi
Kdd 2014 tutorial   bringing structure to text - chiKdd 2014 tutorial   bringing structure to text - chi
Kdd 2014 tutorial bringing structure to text - chiBarbara Starr
 
Data science training institute in hyderabad
Data science training institute in hyderabadData science training institute in hyderabad
Data science training institute in hyderabadKelly Technologies
 
Top (10) challenging problems in data mining
Top (10) challenging problems  in data miningTop (10) challenging problems  in data mining
Top (10) challenging problems in data miningAhmedasbasb
 
Semantic Web Investigation within Big Data Context
Semantic Web Investigation within Big Data ContextSemantic Web Investigation within Big Data Context
Semantic Web Investigation within Big Data ContextMurad Daryousse
 
Lecture Case Studies
Lecture Case StudiesLecture Case Studies
Lecture Case StudiesFleur Deken
 
Spark Social Media
Spark Social Media Spark Social Media
Spark Social Media suresh sood
 
Generating educational assessment items from Linked Open Data
Generating educational assessment items from Linked Open DataGenerating educational assessment items from Linked Open Data
Generating educational assessment items from Linked Open Datachessmu
 
Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...
Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...
Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...Matthew Lease
 
Nicholas Jewell MedicReS World Congress 2014
Nicholas Jewell MedicReS World Congress 2014Nicholas Jewell MedicReS World Congress 2014
Nicholas Jewell MedicReS World Congress 2014MedicReS
 
Data Analysis for Qualitative Research
Data Analysis for Qualitative Research Data Analysis for Qualitative Research
Data Analysis for Qualitative Research Ashley Casey
 
Turning Learning into Numbers - A Learning Analytics Framework
Turning Learning into Numbers - A Learning Analytics FrameworkTurning Learning into Numbers - A Learning Analytics Framework
Turning Learning into Numbers - A Learning Analytics FrameworkHendrik Drachsler
 
What knowledge bases know (and what they don't)
What knowledge bases know (and what they don't)What knowledge bases know (and what they don't)
What knowledge bases know (and what they don't)srazniewski
 
Data Science - An emerging Stream of Science with its Spreading Reach & Impact
Data Science - An emerging Stream of Science with its Spreading Reach & ImpactData Science - An emerging Stream of Science with its Spreading Reach & Impact
Data Science - An emerging Stream of Science with its Spreading Reach & ImpactDr. Sunil Kr. Pandey
 

Similar to WDAqua introduction presentation (20)

From Web Data to Knowledge: on the Complementarity of Human and Artificial In...
From Web Data to Knowledge: on the Complementarity of Human and Artificial In...From Web Data to Knowledge: on the Complementarity of Human and Artificial In...
From Web Data to Knowledge: on the Complementarity of Human and Artificial In...
 
Big Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&DBig Data Talent in Academic and Industry R&D
Big Data Talent in Academic and Industry R&D
 
Broad Data (India 2015)
Broad Data (India 2015)Broad Data (India 2015)
Broad Data (India 2015)
 
Session 01 designing and scoping a data science project
Session 01 designing and scoping a data science projectSession 01 designing and scoping a data science project
Session 01 designing and scoping a data science project
 
Session 01 designing and scoping a data science project
Session 01 designing and scoping a data science projectSession 01 designing and scoping a data science project
Session 01 designing and scoping a data science project
 
Mapping (big) data science (15 dec2014)대학(원)생
Mapping (big) data science (15 dec2014)대학(원)생Mapping (big) data science (15 dec2014)대학(원)생
Mapping (big) data science (15 dec2014)대학(원)생
 
Kdd 2014 tutorial bringing structure to text - chi
Kdd 2014 tutorial   bringing structure to text - chiKdd 2014 tutorial   bringing structure to text - chi
Kdd 2014 tutorial bringing structure to text - chi
 
Data science training institute in hyderabad
Data science training institute in hyderabadData science training institute in hyderabad
Data science training institute in hyderabad
 
Top (10) challenging problems in data mining
Top (10) challenging problems  in data miningTop (10) challenging problems  in data mining
Top (10) challenging problems in data mining
 
Semantic Web Investigation within Big Data Context
Semantic Web Investigation within Big Data ContextSemantic Web Investigation within Big Data Context
Semantic Web Investigation within Big Data Context
 
Intro to Data Science Concepts
Intro to Data Science ConceptsIntro to Data Science Concepts
Intro to Data Science Concepts
 
Lecture Case Studies
Lecture Case StudiesLecture Case Studies
Lecture Case Studies
 
Spark Social Media
Spark Social Media Spark Social Media
Spark Social Media
 
Generating educational assessment items from Linked Open Data
Generating educational assessment items from Linked Open DataGenerating educational assessment items from Linked Open Data
Generating educational assessment items from Linked Open Data
 
Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...
Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...
Designing at the Intersection of HCI & AI: Misinformation & Crowdsourced Anno...
 
Nicholas Jewell MedicReS World Congress 2014
Nicholas Jewell MedicReS World Congress 2014Nicholas Jewell MedicReS World Congress 2014
Nicholas Jewell MedicReS World Congress 2014
 
Data Analysis for Qualitative Research
Data Analysis for Qualitative Research Data Analysis for Qualitative Research
Data Analysis for Qualitative Research
 
Turning Learning into Numbers - A Learning Analytics Framework
Turning Learning into Numbers - A Learning Analytics FrameworkTurning Learning into Numbers - A Learning Analytics Framework
Turning Learning into Numbers - A Learning Analytics Framework
 
What knowledge bases know (and what they don't)
What knowledge bases know (and what they don't)What knowledge bases know (and what they don't)
What knowledge bases know (and what they don't)
 
Data Science - An emerging Stream of Science with its Spreading Reach & Impact
Data Science - An emerging Stream of Science with its Spreading Reach & ImpactData Science - An emerging Stream of Science with its Spreading Reach & Impact
Data Science - An emerging Stream of Science with its Spreading Reach & Impact
 

Recently uploaded

Quarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up FridayQuarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up FridayMakMakNepo
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfSpandanaRallapalli
 
Judging the Relevance and worth of ideas part 2.pptx
Judging the Relevance  and worth of ideas part 2.pptxJudging the Relevance  and worth of ideas part 2.pptx
Judging the Relevance and worth of ideas part 2.pptxSherlyMaeNeri
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatYousafMalik24
 
Roles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceRoles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceSamikshaHamane
 
Gas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptxGas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptxDr.Ibrahim Hassaan
 
DATA STRUCTURE AND ALGORITHM for beginners
DATA STRUCTURE AND ALGORITHM for beginnersDATA STRUCTURE AND ALGORITHM for beginners
DATA STRUCTURE AND ALGORITHM for beginnersSabitha Banu
 
Romantic Opera MUSIC FOR GRADE NINE pptx
Romantic Opera MUSIC FOR GRADE NINE pptxRomantic Opera MUSIC FOR GRADE NINE pptx
Romantic Opera MUSIC FOR GRADE NINE pptxsqpmdrvczh
 
Grade 9 Q4-MELC1-Active and Passive Voice.pptx
Grade 9 Q4-MELC1-Active and Passive Voice.pptxGrade 9 Q4-MELC1-Active and Passive Voice.pptx
Grade 9 Q4-MELC1-Active and Passive Voice.pptxChelloAnnAsuncion2
 
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTiammrhaywood
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfMr Bounab Samir
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for BeginnersSabitha Banu
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPCeline George
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 

Recently uploaded (20)

Quarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up FridayQuarter 4 Peace-education.pptx Catch Up Friday
Quarter 4 Peace-education.pptx Catch Up Friday
 
ACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdfACC 2024 Chronicles. Cardiology. Exam.pdf
ACC 2024 Chronicles. Cardiology. Exam.pdf
 
Judging the Relevance and worth of ideas part 2.pptx
Judging the Relevance  and worth of ideas part 2.pptxJudging the Relevance  and worth of ideas part 2.pptx
Judging the Relevance and worth of ideas part 2.pptx
 
Model Call Girl in Bikash Puri Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Bikash Puri  Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Bikash Puri  Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Bikash Puri Delhi reach out to us at 🔝9953056974🔝
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice great
 
Roles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceRoles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in Pharmacovigilance
 
Gas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptxGas measurement O2,Co2,& ph) 04/2024.pptx
Gas measurement O2,Co2,& ph) 04/2024.pptx
 
Raw materials used in Herbal Cosmetics.pptx
Raw materials used in Herbal Cosmetics.pptxRaw materials used in Herbal Cosmetics.pptx
Raw materials used in Herbal Cosmetics.pptx
 
DATA STRUCTURE AND ALGORITHM for beginners
DATA STRUCTURE AND ALGORITHM for beginnersDATA STRUCTURE AND ALGORITHM for beginners
DATA STRUCTURE AND ALGORITHM for beginners
 
Romantic Opera MUSIC FOR GRADE NINE pptx
Romantic Opera MUSIC FOR GRADE NINE pptxRomantic Opera MUSIC FOR GRADE NINE pptx
Romantic Opera MUSIC FOR GRADE NINE pptx
 
Grade 9 Q4-MELC1-Active and Passive Voice.pptx
Grade 9 Q4-MELC1-Active and Passive Voice.pptxGrade 9 Q4-MELC1-Active and Passive Voice.pptx
Grade 9 Q4-MELC1-Active and Passive Voice.pptx
 
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPTECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
ECONOMIC CONTEXT - LONG FORM TV DRAMA - PPT
 
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdfLike-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
Like-prefer-love -hate+verb+ing & silent letters & citizenship text.pdf
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
OS-operating systems- ch04 (Threads) ...
OS-operating systems- ch04 (Threads) ...OS-operating systems- ch04 (Threads) ...
OS-operating systems- ch04 (Threads) ...
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for Beginners
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERP
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 

WDAqua introduction presentation

  • 1. Handling Dynamicity and Temporality of Web Data Hady Elsahar hadyelsahar@gmail.com Jean Monnet University Saint-Étienne, France
  • 2. First try with Question Answering Weet it : Natural language interface for Linked Data (ElSahar et al. ‘11 )
  • 3. ● Most of the current knowledge bases focus on static facts and ignore the temporal dimension of facts. ● Aspects of temporality and Dynamicity of Datasets : ○ Aspect 1 : Many facts are valid only during a particular time period. ○ Aspect 2 : New extracted facts can contradict with, verify or modify new ones ○ Aspect 3 : Some Facts are collectively induced from a series of Events Handling Dynamicity of Data
  • 4. Challenges and Motivations (1) : Stephen Hawking Many facts are valid only during a particular time period. Use Case : Questions about Temporal facts ● Who is first Wife of Stephen Hawiking ? ● Who is the 10th President of France ? ● Who is the past CEO of google ?
  • 5. Extraction and Represenation of Temporal data Extraction and representation of Temporal Facts and Events ❏ Representation : ❏ Keeping the last updated fact is not enough (DBpedia) ❏ Higher order fact (Erdal and Weikum ‘11) ❏ f1:Bill_Clinton isPresidentOf USA. ❏ f2:f1 startedOnDate 20-01-1993 ❏ Wikidata Qualifiers (Vrandečić ‘12) ❏ Temporal fact and event extraction: ❏ Free Text and structured data from wikipedia (patterns and pattern induction) (Erdal and Weikum ‘11)
  • 6. Annotation of temporal facts in documents for Question answering SemEval-2015 Task 5: QA TempEval
  • 7. SemEval-2015 Task 5: QA TempEval Question Examples in the Evaluation Dataset : Yes / No: ● “Did the the Indonesian stock market rise again after it’s last fall ? List: ● “What happened after the crash?” ● “What happened between the crash and yesterday?” When (Factoid): ● “When did the Oscar ceremony end yesterday ?” Applications ?
  • 8. Challenges and Motivations (2) : Stephen Hawking In Highly dynamic datasets, new extracted facts can contradict with, verify or modify new ones. Existing facts New Extracted Fact Matt Smith is dbo:starring of ■ dbr:Womb_(film) ■ dbr:Lost_River_(film) ■ dbr:Bert_and_Dickie ■ dbr:The_Science_of_Doctor_Who “Matt Smith is the doctor” (Matt Smith, occupation, Medicine) confidence : 0.1
  • 9. (Frank Sinatra, profession, Singer) confidence : 0.9 (Jared leto, influenced_by, Frank Sinatra) confidence : 0.8 ● People influenced by Writers are probably writers as well ● people are probably born at the same place of their siblings Challenges and Motivations (2) : Stephen Hawking In Highly dynamic datasets, new extracted facts can contradict with, verify or modify new ones.
  • 10. Evaluation of new facts using Link prediction Link Prediction ● Add new facts without extra knowledge ● Assess the validity of an unknown fact
  • 11. Embedding Models for knowledge bases TransE : Modeling Relations as Translations (Bordes et al. ’13): ● Modeling Facts as translations between vectors of entities VSubject + VRelation ≅ VObject ● distance is used to Quantify confidence in facts ● Training objective: Find the representations that Minimizes distances across all true facts and maximize across “corrupted” facts ( s’ , o’ ):
  • 12. Other Embedding Models: ● Structured Embeddings (SE) (Bordes et al ‘11 ) ● Collective Matrix Factorization (RESCAL) (Nickel et al., ’11) ● Neural Tensor Networks (socher et al. ‘13) ● TATEC (Garcia-Duran et al., ’14) Embedding Models for Text + Knowledge bases: ● Joint Learning of Words and Meaning Representations (Bordes et al. ‘12) ● Knowledge Graph and Text Jointly Embedding (Wang et al ‘14) Link prediction using Embedding Models
  • 13. Applications ? ● Verification of new Extracted Facts ● Completeness of new added datasets ● Modeing literals dataypes (length, date ..etc ) not only relations and entities. Embedding Models other benefits ? (collaboration potential) ● Entity Disambiguation for Fact Extraction and QA (Bordes et al. ‘12) ● Paraphrase Detection for Questions, (PARALEX) (Fader et al. ‘13)
  • 14. Challenges and Motivations (3) : Reasoning with more than one supporting facts ● Reasoning about positions (ex: Geo Data) ● Reasoning about Counts ● Reasoning about sizesFact 1 : 55 passengers crammed into the smuggler’s boat. Fact 2 : The boat made it to the Greek island. Question : Where are the passengers ? Stephen Hawking Facts induced from a series of Events ● Towards AI-Complete QA: A Set of Prerequisite Toy Tasks (Wetson et al ‘15) ● Memory Networks (Wetson et al ‘14)