SlideShare une entreprise Scribd logo
1  sur  29
Co-funded by the European Union
QALL-ME: Ontology andQALL-ME: Ontology and
Semantic WebSemantic Web
Constantin Orasan
University of Wolverhampton
http://clg.wlv.ac.uk
Structure of presentation
1. The QALL-ME ontology
2. The ontology for answer retrieval
3. The ontology for bibliographical domain
4. The ontology for presentation
5. Where next?
Author, Title - Date 3
Ontology in QALL-MEOntology in QALL-ME
 The QALL-ME ontology provides a
conceptualised description of the domain in
which the system is used
 It is used to:
 Provide a bridge between languages
 Pass information between different components
of the system
 Encode the data
 Retrieve the data
QALL-ME ontology
 An ontology for the domain of tourism was
developed and used in the prototype (Ou et.
al., 2008)
 Experiments with (existing) ontologies for the
bibliographical domain were carried out
(Orasan et. al., 2009)
Ontology for the domain of tourism
 Developed to address the user needs
 Inspired by existing ontologies such as
Harmonise, eTourism, etc.
 … but developed specially for the project
 Aligned it to WordNet and SUMO
 Freely available from the QALL-ME website
Part of the ontology (cinema/movies)
Semantic annotation and database organization
 The ontology was used to encode the data
 Annotated data from the content providers
was converted to RDF triplets
 The RDF documents can be stored in
databases or plain text files
 The Jena RDF API was used for the
operations
Semantic annotation and database organization
XML Schema
XML
Documents
RDF
Documents
Define
DetermineDetermine
Transform
QALL-ME
Ontology
HTML
Parser
Download World Wide
Web
Convert
Database
Convert
Ontology for answer retrieval
What movie starring Halle Berry is on in Birmingham?
Class: MovieShow 
Property: isInSite, Range: Cinema 
Property: hasPostalAddress, Range: PostalAddress 
Property: isInDestination, Range: Destination
Property: name, Range: string <Birmingham>
Property: hasEventContent, Range: Movie 
Property: name, Range: string <unknown>
Property: hasStar, Range: Star 
Property:name, Range: string <Halle Berry>
PREFIX qme: http://qallme.itc.it/ontology/qallme-tourism.owl#
PREFIX xsd: http://www.w3.org/2001/XMLSchema#
SELECT ?movieName
WHERE {
?MovieShow qme:isInSite ?Cinema.
?Cinema qme:hasPostalAddress ?PostalAddress.
?PostalAddress qme:isInDestination ?Destination.
?Destination qme:name “Birmingham”^^<xsd:string>
?MovieShow qme:hasEventContent ?Movie.
?Movie qme:name ?movieName.
?Movie qme:hasStar ?Star.
?Star qme:name “Halle Berry”^^<xsd:string>
}
Ontology for MRP
 Minimal Relation Patterns represent relations
in the ontology
 Can be used in text entailment
 Already presented
Ontology for generation of hypothesis
 Starting from the ontology we can create hypothesis
What is the name of the movie with [DIRECTOR]?
What is the director of the movie with the name [NAME]?
 Can be done for any language
 Can generate the SPARQL at the same time
 Can be done for any domain
Ontology generated patterns
 91% of the questions from the benchmark have one
or two constrains
 Investigation of the benchmark indicated three
types of questions:
 T1 – Query the name of a site or event which has one or
more non-name attributes;
Can you tell me the name of a Chinese restaurant in
Walsall?
 T2 – Query a non-name attribute of a site or event whose
name is known; and
Can you give me the address for the Kinnaree Thai
Restaurant?
 T3 – Query a non-name attribute of a site or event whose
name is unknown but using its other non-name
attribute(s) as the constraint(s).
Could you give me a contact number for an
Italian restaurant in Solihull?”
 can be decomposed into the following two
questions:
 T1: could you give me the name of an Italian
restaurant in Solihull?
 T2: could you give me a contact number for
<the name of the restaurant in T1>?
Automatically generated patterns
 the ontology can be used to generate patterns for T1 and
T2 questions with one or two constraints
 2703 patterns were generated for English and German
 generated also the SPARQLs
 Evaluation on 200 questions
 Baseline = cosine bag of words
 Semantic engine = similarity on concepts + EAT + entity
filtering
 Language and domain independent
Baseline Semantic engine
English 42.46% 65%
German 34.96% 64.88%
How do we move to another
domain?
Domain of scientific publications
 Experiments for the bibliographic domain were
carried out
What papers did C. Orasan published in 2008?
 Existing ontologies were combined:
 Semantic Web for Research Communities (SWRC)
models concepts from the research community
 A subset of Dublin Core was used to describe the
properties of a bibliographical entry
 Simple Knowledge Organisation System (SKOS) was
used to model relations between terms
 The data from BibTeX format was converted
to the domain ontology
 SPARQL patterns were generated
 The retrieval algorithm was not changed
 … but some changes had to be introduced at
the level of framework
How do we interact with the
user?
 User satisfaction is largely determined by
aspects such as the ease of use, learning
curve, feedback, interface friendliness, etc.
and not just by accuracy.
What movies can I see at Symphony Hall this week?
 If no answers:
 Look for a different location
 Search for a different time period
 Wrong presupposition
 User preferences
 Most of the Feedback desiderata can be met
without changing the current pipeline.
 'understanding' occurs in the Entailment engine
(EE)
 the QPlanner does not have direct access to this
information, but
 it can be injected in the results via the generated
SPARQL, exploiting the RDF data model
 Interactive Question Answering (IQA)
ontology (Magnini et. al., 2009)
 A question is analysed in terms of:
 Expected answer type
 Constraints
 Context
 The answer will contain:
 Core Information
 Justification
 Complementary information
 The situation can be handled using a rich SPARQL
 Rewriting rules for the SPARQL in case of empty
answer
PREFIX declarations
CONSTRUCT {
results triples
AnswersObject triples
QuestionInterpretation triples
}
WHERE { OPTIONAL {
selection triples
} . }
qmq:qi rdf:type qmq:QuestionInterpretation;
qmq:hasInterpretation
"In which cinema is [MOVIE] showed on [TIME]" ;
qmq:hasConstraint qmq:c1;
qmq:hasConstraint qmq:c2;
qmq:hasFacet qmq:f1.
qmq:c2 rdf:type qmq:Filter;
qmq:hasType qmo:DatePeriod;
qmq:hasProperty qmo:startDate;
qmq:hasValue '''[TIMEX2]''' ;
qmq:failureReason
“No film can be for the given date”.
Faceted browsing
Where next?
 We have the technology to “convert” a
natural language question to SPARQL, via
an ontology
 We can get access to a large number of
resources using Linked Open Data
 We can expand the access to knowledge
Thank you !

Contenu connexe

Tendances

Profile-based Dataset Recommendation for RDF Data Linking
Profile-based Dataset Recommendation for RDF Data Linking  Profile-based Dataset Recommendation for RDF Data Linking
Profile-based Dataset Recommendation for RDF Data Linking
Mohamed BEN ELLEFI
 
Tools and Techniques for Analyzing Texts: Tweets to Intellectual Property
Tools and Techniques for Analyzing Texts: Tweets to Intellectual PropertyTools and Techniques for Analyzing Texts: Tweets to Intellectual Property
Tools and Techniques for Analyzing Texts: Tweets to Intellectual Property
Dan Sullivan, Ph.D.
 
EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...
EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...
EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...
Francesco Osborne
 

Tendances (20)

Profile-based Dataset Recommendation for RDF Data Linking
Profile-based Dataset Recommendation for RDF Data Linking  Profile-based Dataset Recommendation for RDF Data Linking
Profile-based Dataset Recommendation for RDF Data Linking
 
Automatic Classification of Springer Nature Proceedings with Smart Topic Miner
Automatic Classification of Springer Nature Proceedings with Smart Topic MinerAutomatic Classification of Springer Nature Proceedings with Smart Topic Miner
Automatic Classification of Springer Nature Proceedings with Smart Topic Miner
 
NLP & DBpedia
 NLP & DBpedia NLP & DBpedia
NLP & DBpedia
 
Spoken Content Retrieval - Lattices and Beyond
Spoken Content Retrieval - Lattices and BeyondSpoken Content Retrieval - Lattices and Beyond
Spoken Content Retrieval - Lattices and Beyond
 
Aspects of NLP Practice
Aspects of NLP PracticeAspects of NLP Practice
Aspects of NLP Practice
 
Apply chinese radicals into neural machine translation: deeper than character...
Apply chinese radicals into neural machine translation: deeper than character...Apply chinese radicals into neural machine translation: deeper than character...
Apply chinese radicals into neural machine translation: deeper than character...
 
BDACA1617s2 - Lecture 2
BDACA1617s2 - Lecture 2BDACA1617s2 - Lecture 2
BDACA1617s2 - Lecture 2
 
FaCoY – A Code-to-Code Search Engine
FaCoY – A Code-to-Code Search EngineFaCoY – A Code-to-Code Search Engine
FaCoY – A Code-to-Code Search Engine
 
BDACA1617s2 - Tutorial 1
BDACA1617s2 - Tutorial 1BDACA1617s2 - Tutorial 1
BDACA1617s2 - Tutorial 1
 
The State of #NLProc
The State of #NLProcThe State of #NLProc
The State of #NLProc
 
Practical machine learning - Part 1
Practical machine learning - Part 1Practical machine learning - Part 1
Practical machine learning - Part 1
 
Tools and Techniques for Analyzing Texts: Tweets to Intellectual Property
Tools and Techniques for Analyzing Texts: Tweets to Intellectual PropertyTools and Techniques for Analyzing Texts: Tweets to Intellectual Property
Tools and Techniques for Analyzing Texts: Tweets to Intellectual Property
 
BDACA1617s2 - Lecture3
BDACA1617s2 - Lecture3BDACA1617s2 - Lecture3
BDACA1617s2 - Lecture3
 
GLOBE Metadata Analysis
GLOBE Metadata AnalysisGLOBE Metadata Analysis
GLOBE Metadata Analysis
 
Vivo Search
Vivo SearchVivo Search
Vivo Search
 
NLP and LSA getting started
NLP and LSA getting startedNLP and LSA getting started
NLP and LSA getting started
 
EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...
EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...
EKAW 2016 - Ontology Forecasting in Scientific Literature: Semantic Concepts ...
 
NLP Project Full Cycle
NLP Project Full CycleNLP Project Full Cycle
NLP Project Full Cycle
 
Supporting Springer Nature Editors by means of Semantic Technologies
Supporting Springer Nature Editors by means of Semantic TechnologiesSupporting Springer Nature Editors by means of Semantic Technologies
Supporting Springer Nature Editors by means of Semantic Technologies
 
WISS QA Do it yourself Question answering over Linked Data
WISS QA Do it yourself Question answering over Linked DataWISS QA Do it yourself Question answering over Linked Data
WISS QA Do it yourself Question answering over Linked Data
 

En vedette

Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012
Peter Mika
 

En vedette (20)

Application of Ontology in Semantic Information Retrieval by Prof Shahrul Azm...
Application of Ontology in Semantic Information Retrieval by Prof Shahrul Azm...Application of Ontology in Semantic Information Retrieval by Prof Shahrul Azm...
Application of Ontology in Semantic Information Retrieval by Prof Shahrul Azm...
 
Implementing Semantic Search
Implementing Semantic SearchImplementing Semantic Search
Implementing Semantic Search
 
Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012
 
Semantic Web For Distributed Social Networks
Semantic Web For Distributed Social NetworksSemantic Web For Distributed Social Networks
Semantic Web For Distributed Social Networks
 
The Semantic Web: 2010 Update
The Semantic Web: 2010 Update The Semantic Web: 2010 Update
The Semantic Web: 2010 Update
 
Building OBO Foundry ontology using semantic web tools
Building OBO Foundry ontology using semantic web toolsBuilding OBO Foundry ontology using semantic web tools
Building OBO Foundry ontology using semantic web tools
 
Ontology Web services for Semantic Applications
Ontology Web services for Semantic ApplicationsOntology Web services for Semantic Applications
Ontology Web services for Semantic Applications
 
Practical Semantic Web and Why You Should Care - DrupalCon DC 2009
Practical Semantic Web and Why You Should Care - DrupalCon DC 2009Practical Semantic Web and Why You Should Care - DrupalCon DC 2009
Practical Semantic Web and Why You Should Care - DrupalCon DC 2009
 
Ontology, Semantic Web and DBpedia
Ontology, Semantic Web and DBpediaOntology, Semantic Web and DBpedia
Ontology, Semantic Web and DBpedia
 
The Semantic Web (and what it can deliver for your business)
The Semantic Web (and what it can deliver for your business)The Semantic Web (and what it can deliver for your business)
The Semantic Web (and what it can deliver for your business)
 
SMWCon Fall 2015 FForms
SMWCon Fall 2015 FFormsSMWCon Fall 2015 FForms
SMWCon Fall 2015 FForms
 
Introduction To The Semantic Web
Introduction To The Semantic  WebIntroduction To The Semantic  Web
Introduction To The Semantic Web
 
Real-time Semantic Web with Twitter Annotations
Real-time Semantic Web with Twitter AnnotationsReal-time Semantic Web with Twitter Annotations
Real-time Semantic Web with Twitter Annotations
 
Introduction to the Semantic Web
Introduction to the Semantic WebIntroduction to the Semantic Web
Introduction to the Semantic Web
 
The Standardization of Semantic Web Ontology
The Standardization of Semantic Web OntologyThe Standardization of Semantic Web Ontology
The Standardization of Semantic Web Ontology
 
The semantic web
The semantic webThe semantic web
The semantic web
 
Semantic Web
Semantic WebSemantic Web
Semantic Web
 
Introduction to the Semantic Web
Introduction to the Semantic WebIntroduction to the Semantic Web
Introduction to the Semantic Web
 
The GoodRelations Ontology: Making Semantic Web-based E-Commerce a Reality
The GoodRelations Ontology: Making Semantic  Web-based E-Commerce a RealityThe GoodRelations Ontology: Making Semantic  Web-based E-Commerce a Reality
The GoodRelations Ontology: Making Semantic Web-based E-Commerce a Reality
 
Semantic Web
Semantic WebSemantic Web
Semantic Web
 

Similaire à QALL-ME: Ontology and Semantic Web

Finding knowledge, data and answers on the Semantic Web
Finding knowledge, data and answers on the Semantic WebFinding knowledge, data and answers on the Semantic Web
Finding knowledge, data and answers on the Semantic Web
ebiquity
 
Tracing Networks: Ontology-based Software in a Nutshell
Tracing Networks: Ontology-based Software in a NutshellTracing Networks: Ontology-based Software in a Nutshell
Tracing Networks: Ontology-based Software in a Nutshell
TracingNetworks
 
Sem facet paper
Sem facet paperSem facet paper
Sem facet paper
DBOnto
 
Tracing Networks: Ontology Software in a Nutshell
Tracing Networks: Ontology Software in a NutshellTracing Networks: Ontology Software in a Nutshell
Tracing Networks: Ontology Software in a Nutshell
enoch1982
 
Using the Semantic Web, and Contributing to it
Using the Semantic Web, and Contributing to itUsing the Semantic Web, and Contributing to it
Using the Semantic Web, and Contributing to it
Mathieu d'Aquin
 

Similaire à QALL-ME: Ontology and Semantic Web (20)

Finding knowledge, data and answers on the Semantic Web
Finding knowledge, data and answers on the Semantic WebFinding knowledge, data and answers on the Semantic Web
Finding knowledge, data and answers on the Semantic Web
 
Reasoning on the Semantic Web
Reasoning on the Semantic WebReasoning on the Semantic Web
Reasoning on the Semantic Web
 
(Re-) Discovering Lost Web Pages
(Re-) Discovering Lost Web Pages(Re-) Discovering Lost Web Pages
(Re-) Discovering Lost Web Pages
 
(Re-)Discovering Lost Web Pages
(Re-)Discovering Lost Web Pages(Re-)Discovering Lost Web Pages
(Re-)Discovering Lost Web Pages
 
Synchronicity: Just-In-Time Discovery of Lost Web Pages
Synchronicity: Just-In-Time Discovery of Lost Web PagesSynchronicity: Just-In-Time Discovery of Lost Web Pages
Synchronicity: Just-In-Time Discovery of Lost Web Pages
 
Integrating a Domain Ontology Development Environment and an Ontology Search ...
Integrating a Domain Ontology Development Environment and an Ontology Search ...Integrating a Domain Ontology Development Environment and an Ontology Search ...
Integrating a Domain Ontology Development Environment and an Ontology Search ...
 
Tracing Networks: Ontology-based Software in a Nutshell
Tracing Networks: Ontology-based Software in a NutshellTracing Networks: Ontology-based Software in a Nutshell
Tracing Networks: Ontology-based Software in a Nutshell
 
247th ACS Meeting: Experiment Markup Language (ExptML)
247th ACS Meeting: Experiment Markup Language (ExptML)247th ACS Meeting: Experiment Markup Language (ExptML)
247th ACS Meeting: Experiment Markup Language (ExptML)
 
Building Semantic Web Portals with WebML
Building Semantic Web Portals with WebMLBuilding Semantic Web Portals with WebML
Building Semantic Web Portals with WebML
 
BioSD Tutorial 2014 Editition
BioSD Tutorial 2014 EdititionBioSD Tutorial 2014 Editition
BioSD Tutorial 2014 Editition
 
Sem facet paper
Sem facet paperSem facet paper
Sem facet paper
 
SemFacet paper
SemFacet paperSemFacet paper
SemFacet paper
 
Querying the Web of Data
Querying the Web of DataQuerying the Web of Data
Querying the Web of Data
 
Semantic Web: From Representations to Applications
Semantic Web: From Representations to ApplicationsSemantic Web: From Representations to Applications
Semantic Web: From Representations to Applications
 
Can’t Find Your 404s?
Can’t Find Your 404s?Can’t Find Your 404s?
Can’t Find Your 404s?
 
NCBO BioPortal SPARQL Endpoint - The Quad Economy of a Semantic Web Ontology ...
NCBO BioPortal SPARQL Endpoint - The Quad Economy of a Semantic Web Ontology ...NCBO BioPortal SPARQL Endpoint - The Quad Economy of a Semantic Web Ontology ...
NCBO BioPortal SPARQL Endpoint - The Quad Economy of a Semantic Web Ontology ...
 
Tracing Networks: Ontology Software in a Nutshell
Tracing Networks: Ontology Software in a NutshellTracing Networks: Ontology Software in a Nutshell
Tracing Networks: Ontology Software in a Nutshell
 
Using the Semantic Web, and Contributing to it
Using the Semantic Web, and Contributing to itUsing the Semantic Web, and Contributing to it
Using the Semantic Web, and Contributing to it
 
Toward Semantic Representation of Science in Electronic Laboratory Notebooks ...
Toward Semantic Representation of Science in Electronic Laboratory Notebooks ...Toward Semantic Representation of Science in Electronic Laboratory Notebooks ...
Toward Semantic Representation of Science in Electronic Laboratory Notebooks ...
 
Towards ubiquitous OWL computing: Simplifying programmatic authoring of and q...
Towards ubiquitous OWL computing: Simplifying programmatic authoring of and q...Towards ubiquitous OWL computing: Simplifying programmatic authoring of and q...
Towards ubiquitous OWL computing: Simplifying programmatic authoring of and q...
 

Plus de Constantin Orasan

New trends in NLP applications
New trends in NLP applicationsNew trends in NLP applications
New trends in NLP applications
Constantin Orasan
 

Plus de Constantin Orasan (7)

New trends in NLP applications
New trends in NLP applicationsNew trends in NLP applications
New trends in NLP applications
 
The role of linguistic information for shallow language processing
The role of linguistic information for shallow language processingThe role of linguistic information for shallow language processing
The role of linguistic information for shallow language processing
 
What is Computer-Aided Summarisation and does it really work?
What is Computer-Aided Summarisation and does it really work?What is Computer-Aided Summarisation and does it really work?
What is Computer-Aided Summarisation and does it really work?
 
Tutorial on automatic summarization
Tutorial on automatic summarizationTutorial on automatic summarization
Tutorial on automatic summarization
 
Message project leaflet
Message project leafletMessage project leaflet
Message project leaflet
 
Porting the QALL-ME framework to Romanian
Porting the QALL-ME framework to RomanianPorting the QALL-ME framework to Romanian
Porting the QALL-ME framework to Romanian
 
Annotation of anaphora and coreference for automatic processing
Annotation of anaphora and coreference for automatic processingAnnotation of anaphora and coreference for automatic processing
Annotation of anaphora and coreference for automatic processing
 

Dernier

+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@
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 
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
 

Dernier (20)

+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...
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
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...
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
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
 
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
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 

QALL-ME: Ontology and Semantic Web

  • 1. Co-funded by the European Union QALL-ME: Ontology andQALL-ME: Ontology and Semantic WebSemantic Web Constantin Orasan University of Wolverhampton http://clg.wlv.ac.uk
  • 2. Structure of presentation 1. The QALL-ME ontology 2. The ontology for answer retrieval 3. The ontology for bibliographical domain 4. The ontology for presentation 5. Where next?
  • 3. Author, Title - Date 3 Ontology in QALL-MEOntology in QALL-ME  The QALL-ME ontology provides a conceptualised description of the domain in which the system is used  It is used to:  Provide a bridge between languages  Pass information between different components of the system  Encode the data  Retrieve the data
  • 4. QALL-ME ontology  An ontology for the domain of tourism was developed and used in the prototype (Ou et. al., 2008)  Experiments with (existing) ontologies for the bibliographical domain were carried out (Orasan et. al., 2009)
  • 5. Ontology for the domain of tourism  Developed to address the user needs  Inspired by existing ontologies such as Harmonise, eTourism, etc.  … but developed specially for the project  Aligned it to WordNet and SUMO  Freely available from the QALL-ME website
  • 6. Part of the ontology (cinema/movies)
  • 7. Semantic annotation and database organization  The ontology was used to encode the data  Annotated data from the content providers was converted to RDF triplets  The RDF documents can be stored in databases or plain text files  The Jena RDF API was used for the operations
  • 8. Semantic annotation and database organization XML Schema XML Documents RDF Documents Define DetermineDetermine Transform QALL-ME Ontology HTML Parser Download World Wide Web Convert Database Convert
  • 10. What movie starring Halle Berry is on in Birmingham? Class: MovieShow  Property: isInSite, Range: Cinema  Property: hasPostalAddress, Range: PostalAddress  Property: isInDestination, Range: Destination Property: name, Range: string <Birmingham> Property: hasEventContent, Range: Movie  Property: name, Range: string <unknown> Property: hasStar, Range: Star  Property:name, Range: string <Halle Berry>
  • 11. PREFIX qme: http://qallme.itc.it/ontology/qallme-tourism.owl# PREFIX xsd: http://www.w3.org/2001/XMLSchema# SELECT ?movieName WHERE { ?MovieShow qme:isInSite ?Cinema. ?Cinema qme:hasPostalAddress ?PostalAddress. ?PostalAddress qme:isInDestination ?Destination. ?Destination qme:name “Birmingham”^^<xsd:string> ?MovieShow qme:hasEventContent ?Movie. ?Movie qme:name ?movieName. ?Movie qme:hasStar ?Star. ?Star qme:name “Halle Berry”^^<xsd:string> }
  • 12. Ontology for MRP  Minimal Relation Patterns represent relations in the ontology  Can be used in text entailment  Already presented
  • 13. Ontology for generation of hypothesis  Starting from the ontology we can create hypothesis What is the name of the movie with [DIRECTOR]? What is the director of the movie with the name [NAME]?  Can be done for any language  Can generate the SPARQL at the same time  Can be done for any domain
  • 14. Ontology generated patterns  91% of the questions from the benchmark have one or two constrains  Investigation of the benchmark indicated three types of questions:  T1 – Query the name of a site or event which has one or more non-name attributes; Can you tell me the name of a Chinese restaurant in Walsall?  T2 – Query a non-name attribute of a site or event whose name is known; and Can you give me the address for the Kinnaree Thai Restaurant?  T3 – Query a non-name attribute of a site or event whose name is unknown but using its other non-name attribute(s) as the constraint(s).
  • 15. Could you give me a contact number for an Italian restaurant in Solihull?”  can be decomposed into the following two questions:  T1: could you give me the name of an Italian restaurant in Solihull?  T2: could you give me a contact number for <the name of the restaurant in T1>?
  • 16. Automatically generated patterns  the ontology can be used to generate patterns for T1 and T2 questions with one or two constraints  2703 patterns were generated for English and German  generated also the SPARQLs  Evaluation on 200 questions  Baseline = cosine bag of words  Semantic engine = similarity on concepts + EAT + entity filtering  Language and domain independent Baseline Semantic engine English 42.46% 65% German 34.96% 64.88%
  • 17. How do we move to another domain?
  • 18. Domain of scientific publications  Experiments for the bibliographic domain were carried out What papers did C. Orasan published in 2008?  Existing ontologies were combined:  Semantic Web for Research Communities (SWRC) models concepts from the research community  A subset of Dublin Core was used to describe the properties of a bibliographical entry  Simple Knowledge Organisation System (SKOS) was used to model relations between terms
  • 19.  The data from BibTeX format was converted to the domain ontology  SPARQL patterns were generated  The retrieval algorithm was not changed  … but some changes had to be introduced at the level of framework
  • 20. How do we interact with the user?
  • 21.  User satisfaction is largely determined by aspects such as the ease of use, learning curve, feedback, interface friendliness, etc. and not just by accuracy. What movies can I see at Symphony Hall this week?  If no answers:  Look for a different location  Search for a different time period  Wrong presupposition  User preferences
  • 22.  Most of the Feedback desiderata can be met without changing the current pipeline.  'understanding' occurs in the Entailment engine (EE)  the QPlanner does not have direct access to this information, but  it can be injected in the results via the generated SPARQL, exploiting the RDF data model  Interactive Question Answering (IQA) ontology (Magnini et. al., 2009)
  • 23.  A question is analysed in terms of:  Expected answer type  Constraints  Context  The answer will contain:  Core Information  Justification  Complementary information  The situation can be handled using a rich SPARQL  Rewriting rules for the SPARQL in case of empty answer
  • 24. PREFIX declarations CONSTRUCT { results triples AnswersObject triples QuestionInterpretation triples } WHERE { OPTIONAL { selection triples } . }
  • 25. qmq:qi rdf:type qmq:QuestionInterpretation; qmq:hasInterpretation "In which cinema is [MOVIE] showed on [TIME]" ; qmq:hasConstraint qmq:c1; qmq:hasConstraint qmq:c2; qmq:hasFacet qmq:f1. qmq:c2 rdf:type qmq:Filter; qmq:hasType qmo:DatePeriod; qmq:hasProperty qmo:startDate; qmq:hasValue '''[TIMEX2]''' ; qmq:failureReason “No film can be for the given date”.
  • 27. Where next?  We have the technology to “convert” a natural language question to SPARQL, via an ontology  We can get access to a large number of resources using Linked Open Data  We can expand the access to knowledge
  • 28.