SlideShare una empresa de Scribd logo
1 de 20
Descargar para leer sin conexión
Creating Knowledge out of Interlinked Data
           LOD2 Plenary Vienna – 2012/03/21 – Page 1                  http://lod2.eu




      Plenary Vienna – State-of-Play
      WP3: Knowledge Base Creation,
      Enrichment and Repair




                                                          Jens Lehmann
                                                       AKSW, Universität Leipzig
LOD2 Presentation . 02.09.2010 . Page                              http://lod2.eu
LOD2 Plenary Vienna – 2012/03/21 – Page 2                                 http://lod2.eu




                 WP3 High Level Objectives

                                                                 Inc
8 Tasks, 9 Partners, 14 Deliverables, 20+ tools                      ons
                                                                         ist   enc
→ lightweight integration via LOD2 stack                 Modelling                 y
                                                         Problems

                                                               Repair
          Mutual Refinement Cycle (with                         Refactoring
          optional Extraction phase)



    Structured          Semi-                                         Property-
                     structured                                        Axioms
         Extraction                                          Definitions

                                                              Enrichment

                Un-
                                                                   Data
            structured
                                                                 Summary
LOD2 Plenary Vienna – 2012/03/21 – Page 3             http://lod2.eu




                WP3 Task 3.1
●
    Provenance-Aware Extraction of Linked Data from Existing Structured
    Formats
●
    Partners: FUB, ULEI, OpenLink, Exalead
●
    Development and Support of RDB2RDF mapping standards (R2RML)
●
    Re-Use of existing tools/frameworks:
    ●
        D2R (FUB)
    ●
        Triplify (ULEI)
    ●
        Virtuoso Sponger and RDF Views (OpenLink)
●
    New Tool: Sparqlify
●
    Deliverables: State-of-the Art Report (M6), D2R release (M20), Triplify
    release (M20)
LOD2 Plenary Vienna – 2012/03/21 – Page 4                     http://lod2.eu




                    WP3 Task 3.1 – Progress / Planned

✔ D3.1.1: state of the art in knowledge extraction from structured sources
    ●
        200+ tools collected at http://data.lod2.eu/2011/tools/
    ●
        http://en.wikipedia.org/wiki/Knowledge_extraction (2000 views/month)

✔ D3.1.2: D2R Server MetaData Extension (allows adding licencing and
    provenance output to D2R server)
●
        D3.1.3: Sparqlify:
        ●
            1-1 SPARQL-to-SQL-Rewriting
        ●
            DB-Planner has Full Control
        ●
            Easy to Configure
        ●
            Tested on LinkedGeoData
        ●
            Release in 1-2 months


                                                                  D2R Architecture
LOD2 Plenary Vienna – 2012/03/21 – Page 5                        http://lod2.eu




          WP3 Task 3.2

• Provenance-Aware Extraction of Linked Data from Unstructured and
   Semi-Structured Sources (plain text, HTML, wikis, blogs)
• Partners: FUB, ULEI, OpenLink, Exalead, Zemanta, KAIST, UEP
• NLP techniques / text understanding
• Draws on existing tools:
    •   Stanford Parser, ASV toolkit, Ontos API (all external), Zemanta
    •   DBpedia (FUB, ULEI, OpenLink)
• Deliverables: NLP2RDF release (M8), DBpedia Live (M8), DBpedia
   Framework Extension (M27)
• Other: DBpedia Spotlight Release, DBpedia I18n committee founded
LOD2 Plenary Vienna – 2012/03/21 – Page 6                      http://lod2.eu




           WP3 Task 3.2 – NLP2RDF + NIF

• NLP Interchange Format (NIF) is an RDF/OWL-based format to
   combine and chain NLP tools
• NLP2RDF (http://nlp2rdf.org) is a project providing:
     •   Documentation and tutorials
     •   Reference implementations of NIF
     •   Collaboration and mailing lists
• Roadmap of NIF in LOD2:
     •   Integration of Zemanta API (Task 3.7)
     •   BoA – tool for automated hypernym discovery and entity classification
         to ad hoc classes, using Wikipedia and Wordnet
     •   Ex – tool for information extraction from heterogeneous web resources
     •   MultiLingual Extraction (Task 3.6)
LOD2 Plenary Vienna – 2012/03/21 – Page 7   http://lod2.eu




 WP3 Task 3.2 – NLP2RDF + NIF
LOD2 Plenary Vienna – 2012/03/21 – Page 8              http://lod2.eu




          WP3 Task 3.2 – DBpedia Live Motivation

• Wikipedia 7th most popular website (according to alexa.com)
• Covers a variety of disciplines
• DBpedia (from FUB, ULEI, OpenLink):
 ☺ Extracts structured data from Wikipedia
 ☺ Interlinks with other knowledge bases
 ☺ Can answer complex queries
 ☺ Is used in many applications / companies
 Θ Requires manual effort to create a release
 Θ Data is often several months old


               DBpedia Live Synchronisation with Wikipedia
LOD2 Plenary Vienna – 2012/03/21 – Page 9               http://lod2.eu




          WP3 Task 3.2 – DBpedia Live Architecture




• Works on live stream of updates provided by Wikipedia
• Handles live changes of ontology and mappings (explained later)
• Provides public endpoint at http://live.dbpedia.org/sparql and mirrors
LOD2 Plenary Vienna – 2012/03/21 – Page 10               http://lod2.eu




          WP3 Task 3.3

• Knowledge Base Schema Enrichment
• Partners: ULEI
• Suggests OWL Schema Axioms to Knowlege Base Maintainers
   (Definitions, Super Classes, Disjointness, Domain, Range, …)
• Extends DL-Learner (ULEI) machine learning framework
• Tight coupling of Tasks 3.3 (Enrichment) and 3.4 (Repair):
     • Both will be integrated in the ORE tool
     • Iteration of Repair and Enrichment to improve quality
• Adapts existing approaches to work with very large Linked Data
   knowledge bases (incl. SPARQL support)
LOD2 Plenary Vienna – 2012/03/21 – Page 11                     http://lod2.eu




             WP3 Task 3.3: Learning Schema Axioms




Deliverables: D3.3.1 Enrichment Algorithms (M12), D3.3.2 Enrichment User
Interfaces (M24), D3.3.3 Evaluation (M36)
LOD2 Plenary Vienna – 2012/03/21 – Page 12                 http://lod2.eu




           WP3 Task 3.4
• Knowledge Base Repair
• Partners: ULEI, NUIG
• Fix inconsistent knowledge bases, unsatisfiable classes, (some)
    modelling errors, (some) reasoning performance problems
• Draws on a lot of existing work in ontology debugging and extends it
    to knowledge bases in the LOD cloud
• Related to Task 4.3 (Linked Data Quality Assessment)
• Result: ORE tool (together with Task 3.3)
• Deliverables: Report on Modelling Errors/Problems (M6), 1st ORE Release
    (M28), 2nd ORE Release (M40)
LOD2 Plenary Vienna – 2012/03/21 – Page 13                        http://lod2.eu




             WP3 Task 3.4 - Progress
• ORE (ontology repair and enrichment) tool started:
     •   Code: http://code.google.com/p/ore
     •   General Information: http://ore-tool.net
     •   Web Prototype: http://web.ore-tool.net (preliminary)
     •   Included in LOD2 stack

✔   Deliverable 3.4.1 (State of the Art on Modelling Problems) completed:
     •   Comprehensive overview on modelling problems, syntactical and
         semantical errors
     •   One of the conclusions: many tools available but scalability still an issue
     •   ORE will focus on fragment extraction, incremental reasoning, high reuse
         of existing tools and libraries
• work on algorithms for supporting debugging SPARQL endpoints
LOD2 Plenary Vienna – 2012/03/21 – Page 14              http://lod2.eu




           WP3 Task 3.4a
• Knowledge base repair/refactoring based on naming/content patterns
• Partners: UEP
• Started February 2012 as extension to T3.4 (Knowledge base repair
   from logical point of view)
• Long-term goal is to bring the outcomes of the state-of-the-art ontology
   patterns research to the LOD2 Stack
• Result: a component for ORE allowing to detect taxonomic naming →
   discussion in breakout session
• (Anti-)patterns and suggested repairs will be developed until M24
• long term, prominent linked data vocabularies will be analyzed and
   mapped on ontology (content) design patterns
• Will lead to improvement in ontology repair and enrichment (WP3) as
   well as in ontology matching & instance linking (WP4)
LOD2 Plenary Vienna – 2012/03/21 – Page 15              http://lod2.eu




           WP3 Task 3.5

• Web Linkage Validator
• Partners: NUIG, Exalead
• companion tool for unsupervised interlinking of data on the Semantic
   Web
• Dataset owners or authors utilise the tool by submitting their data
   for internal and external linkage analysis
• analytics will be used to perform recommendations and suggestions
   for ways in which they may improve the linkage of their data, e.g.
   suggest to add further properties, more specific property values,
   better specify classes/properties
• Deliverables: Initial Release (M18), LOD2 Stack Component Release
   (M28)
LOD2 Plenary Vienna – 2012/03/21 – Page 16   http://lod2.eu




 WP3 Task 3.5
LOD2 Plenary Vienna – 2012/03/21 – Page 17                      http://lod2.eu




           WP3 Task 3.6

• Multi-Lingual Provenance-Aware Linked Data Extraction
• Partners: IMP
• Information retrieval: find documents using appropriate keywords
   (e.g. search engines: Google, Yahoo!, Baidu, Bing, etc.)
• Functionality not supported: find documents using a natural language
   document instead of using keywords
• Possible applications: Patent search (patent attorneys); Case search
   (lawyers); Anamnesis search (physicians); Paper search (researchers)
• The corresponding NLP technique will enable:
     •   Processing of documents in multiple languages
     •   Extraction of a vocabulary of concepts (words, phrases) specific for each
         class of documents
     •   Representation of domain specific vocabularies and links to related
         documents (based on NIF format)
LOD2 Plenary Vienna – 2012/03/21 – Page 18               http://lod2.eu




           WP3 Task 3.6

• Re-Uses many LOD2 stack components
• NLP technique for the structured representation of natural language
   documents:
     ✔ Representation of natural language documents in structured
       form (words, phrases, sentences, paragraphs, documents)
     • Multi-lingual support based on UTF-8 format – ongoing activity
     • Creation of domain specific vocabularies based on classified
       documents – not started yet
     • Searching for similar documents based on domain specific
       concepts found in given document – not started yet
     • Sorting found documents according to similarity – not started yet
• Deliverables: D3.6 Multi-Lingual Support for Linked Data Extraction
   (M30)
LOD2 Plenary Vienna – 2012/03/21 – Page 19                      http://lod2.eu




          WP3 Task 3.7

• Web Scale Link and Text Mining
• Partners: ZEM
• Gathering shallow semantic data about new entities – new knowledge
   about popular topics (not yet curated in LOD)
• Contributes to WP3 by creating new LOD datasets
    •   Extraction of new entities from blogs worldwide
    •   Creation of lexicons for new entity types to be used in named entity
        extraction engines
• Integration of new LOD datasets in Zemanta recommendation engine
    •   Gain market advantage
    •   Improved recommendations for bloggers and Zemanta free API users
• Deliverables: D3.7.1 Shallow information extraction from blogs (M20),
   D3.7.2 Improved entity recommender engine (M36)
LOD2 Plenary Vienna – 2012/03/21 – Page 20              http://lod2.eu




Thanks for your attention!

     Project: http://lod2.eu
     Organisation: http://uni-leipzig.de, http://aksw.org
     Presenter: http://jens-lehmann.org

Más contenido relacionado

La actualidad más candente

Soren Auer - LOD2 - creating knowledge out of Interlinked Data
Soren Auer - LOD2 - creating knowledge out of Interlinked DataSoren Auer - LOD2 - creating knowledge out of Interlinked Data
Soren Auer - LOD2 - creating knowledge out of Interlinked DataOpen City Foundation
 
Linked Data for Abbreviations and Segmentation
Linked Data for Abbreviations and SegmentationLinked Data for Abbreviations and Segmentation
Linked Data for Abbreviations and SegmentationSebastian Hellmann
 
Standardizing for Open Data
Standardizing for Open DataStandardizing for Open Data
Standardizing for Open DataIvan Herman
 
Setting up Dataverse repository for research data
Setting up Dataverse repository for research dataSetting up Dataverse repository for research data
Setting up Dataverse repository for research datavty
 
Semantic web-and-public-data - en
Semantic web-and-public-data - enSemantic web-and-public-data - en
Semantic web-and-public-data - enTenforce
 
The world of Docker and Kubernetes
The world of Docker and Kubernetes The world of Docker and Kubernetes
The world of Docker and Kubernetes vty
 
Technical integration of data repositories status and challenges
Technical integration of data repositories status and challengesTechnical integration of data repositories status and challenges
Technical integration of data repositories status and challengesvty
 
CLARIN CMDI support in Dataverse
CLARIN CMDI support in Dataverse CLARIN CMDI support in Dataverse
CLARIN CMDI support in Dataverse vty
 
Clariah Tech Day: Controlled Vocabularies and Ontologies in Dataverse
Clariah Tech Day: Controlled Vocabularies and Ontologies in DataverseClariah Tech Day: Controlled Vocabularies and Ontologies in Dataverse
Clariah Tech Day: Controlled Vocabularies and Ontologies in Dataversevty
 
Building Linked Data Applications
Building Linked Data ApplicationsBuilding Linked Data Applications
Building Linked Data ApplicationsEUCLID project
 
Big Linked Data - Creating Training Curricula
Big Linked Data - Creating Training CurriculaBig Linked Data - Creating Training Curricula
Big Linked Data - Creating Training CurriculaEUCLID project
 
External controlled vocabularies support in Dataverse
External controlled vocabularies support in DataverseExternal controlled vocabularies support in Dataverse
External controlled vocabularies support in Dataversevty
 
An introduction to Linked (Open) Data
An introduction to Linked (Open) DataAn introduction to Linked (Open) Data
An introduction to Linked (Open) DataAli Khalili
 
Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891
Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891
Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891FREMEProjectH2020
 

La actualidad más candente (20)

LOD2 Webinar Series: Zemanta / Open refine
LOD2 Webinar Series: Zemanta / Open refine LOD2 Webinar Series: Zemanta / Open refine
LOD2 Webinar Series: Zemanta / Open refine
 
Soren Auer - LOD2 - creating knowledge out of Interlinked Data
Soren Auer - LOD2 - creating knowledge out of Interlinked DataSoren Auer - LOD2 - creating knowledge out of Interlinked Data
Soren Auer - LOD2 - creating knowledge out of Interlinked Data
 
Free Webinar: LOD2 Stack - 1st release
Free Webinar: LOD2 Stack - 1st releaseFree Webinar: LOD2 Stack - 1st release
Free Webinar: LOD2 Stack - 1st release
 
LOD2: State of Play WP3A - Knowledge Base Creation, Enrichment and Repair
LOD2: State of Play WP3A - Knowledge Base Creation, Enrichment and RepairLOD2: State of Play WP3A - Knowledge Base Creation, Enrichment and Repair
LOD2: State of Play WP3A - Knowledge Base Creation, Enrichment and Repair
 
Lod2
Lod2Lod2
Lod2
 
LOD2 webinar series: Virtuoso by OpenLink Software
LOD2 webinar series: Virtuoso by OpenLink SoftwareLOD2 webinar series: Virtuoso by OpenLink Software
LOD2 webinar series: Virtuoso by OpenLink Software
 
Linked Data for Abbreviations and Segmentation
Linked Data for Abbreviations and SegmentationLinked Data for Abbreviations and Segmentation
Linked Data for Abbreviations and Segmentation
 
LOD2: State of Play WP1: Requirements, Design & LOD2 Stack Prototype
LOD2: State of Play WP1: Requirements, Design & LOD2 Stack PrototypeLOD2: State of Play WP1: Requirements, Design & LOD2 Stack Prototype
LOD2: State of Play WP1: Requirements, Design & LOD2 Stack Prototype
 
Standardizing for Open Data
Standardizing for Open DataStandardizing for Open Data
Standardizing for Open Data
 
Setting up Dataverse repository for research data
Setting up Dataverse repository for research dataSetting up Dataverse repository for research data
Setting up Dataverse repository for research data
 
Semantic web-and-public-data - en
Semantic web-and-public-data - enSemantic web-and-public-data - en
Semantic web-and-public-data - en
 
The world of Docker and Kubernetes
The world of Docker and Kubernetes The world of Docker and Kubernetes
The world of Docker and Kubernetes
 
Technical integration of data repositories status and challenges
Technical integration of data repositories status and challengesTechnical integration of data repositories status and challenges
Technical integration of data repositories status and challenges
 
CLARIN CMDI support in Dataverse
CLARIN CMDI support in Dataverse CLARIN CMDI support in Dataverse
CLARIN CMDI support in Dataverse
 
Clariah Tech Day: Controlled Vocabularies and Ontologies in Dataverse
Clariah Tech Day: Controlled Vocabularies and Ontologies in DataverseClariah Tech Day: Controlled Vocabularies and Ontologies in Dataverse
Clariah Tech Day: Controlled Vocabularies and Ontologies in Dataverse
 
Building Linked Data Applications
Building Linked Data ApplicationsBuilding Linked Data Applications
Building Linked Data Applications
 
Big Linked Data - Creating Training Curricula
Big Linked Data - Creating Training CurriculaBig Linked Data - Creating Training Curricula
Big Linked Data - Creating Training Curricula
 
External controlled vocabularies support in Dataverse
External controlled vocabularies support in DataverseExternal controlled vocabularies support in Dataverse
External controlled vocabularies support in Dataverse
 
An introduction to Linked (Open) Data
An introduction to Linked (Open) DataAn introduction to Linked (Open) Data
An introduction to Linked (Open) Data
 
Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891
Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891
Fremeatfeisgiltt2015 fremelinkeddatalocalisers-150603090934-lva1-app6891
 

Similar a LOD2 Plenary Vienna 2012: WP3 - Knowledge Base Creation, Enrichment and Repair

Improving the Performance of the DL-Learner SPARQL Component for Semantic We...
Improving the Performance of the  DL-Learner SPARQL Component for Semantic We...Improving the Performance of the  DL-Learner SPARQL Component for Semantic We...
Improving the Performance of the DL-Learner SPARQL Component for Semantic We...Sebastian Hellmann
 
Linked data and semantic wikis
Linked data and semantic wikisLinked data and semantic wikis
Linked data and semantic wikisSören Auer
 
Integrating NLP using Linked Data
Integrating NLP using Linked DataIntegrating NLP using Linked Data
Integrating NLP using Linked DataSebastian Hellmann
 
Navigation-induced Knowledge Engineering by Example
 Navigation-induced Knowledge Engineering by Example Navigation-induced Knowledge Engineering by Example
Navigation-induced Knowledge Engineering by ExampleSebastian Hellmann
 
WP3 Further specification of Functionality and Interoperability - Gradmann / ...
WP3 Further specification of Functionality and Interoperability - Gradmann / ...WP3 Further specification of Functionality and Interoperability - Gradmann / ...
WP3 Further specification of Functionality and Interoperability - Gradmann / ...Europeana
 
Linked Open Data Visualization
Linked Open Data VisualizationLinked Open Data Visualization
Linked Open Data VisualizationLaura Po
 
Research Object Composer: A Tool for Publishing Complex Data Objects in the C...
Research Object Composer: A Tool for Publishing Complex Data Objects in the C...Research Object Composer: A Tool for Publishing Complex Data Objects in the C...
Research Object Composer: A Tool for Publishing Complex Data Objects in the C...Anita de Waard
 

Similar a LOD2 Plenary Vienna 2012: WP3 - Knowledge Base Creation, Enrichment and Repair (20)

LOD2: State of Play WP5 - Linked Data Visualization, Browsing and Authoring
LOD2: State of Play WP5 - Linked Data Visualization, Browsing and AuthoringLOD2: State of Play WP5 - Linked Data Visualization, Browsing and Authoring
LOD2: State of Play WP5 - Linked Data Visualization, Browsing and Authoring
 
LOD2 Plenary Vienna 2012: WP4 - Reuse, Interlinking and Knowledge Fusion
LOD2 Plenary Vienna 2012: WP4 - Reuse, Interlinking and Knowledge FusionLOD2 Plenary Vienna 2012: WP4 - Reuse, Interlinking and Knowledge Fusion
LOD2 Plenary Vienna 2012: WP4 - Reuse, Interlinking and Knowledge Fusion
 
Improving the Performance of the DL-Learner SPARQL Component for Semantic We...
Improving the Performance of the  DL-Learner SPARQL Component for Semantic We...Improving the Performance of the  DL-Learner SPARQL Component for Semantic We...
Improving the Performance of the DL-Learner SPARQL Component for Semantic We...
 
LOD2 Plenary Vienna 2012: WP2 - Storing and Querying Very Large Knowledge Bases
LOD2 Plenary Vienna 2012: WP2 - Storing and Querying Very Large Knowledge BasesLOD2 Plenary Vienna 2012: WP2 - Storing and Querying Very Large Knowledge Bases
LOD2 Plenary Vienna 2012: WP2 - Storing and Querying Very Large Knowledge Bases
 
LOD2: State of Play WP6 - LOD2 Stack Architecture
LOD2: State of Play WP6 - LOD2 Stack ArchitectureLOD2: State of Play WP6 - LOD2 Stack Architecture
LOD2: State of Play WP6 - LOD2 Stack Architecture
 
Linked data and semantic wikis
Linked data and semantic wikisLinked data and semantic wikis
Linked data and semantic wikis
 
Integrating NLP using Linked Data
Integrating NLP using Linked DataIntegrating NLP using Linked Data
Integrating NLP using Linked Data
 
Navigation-induced Knowledge Engineering by Example
 Navigation-induced Knowledge Engineering by Example Navigation-induced Knowledge Engineering by Example
Navigation-induced Knowledge Engineering by Example
 
LOD2 Webinar Series: SILK
LOD2 Webinar Series: SILKLOD2 Webinar Series: SILK
LOD2 Webinar Series: SILK
 
LOD2 Webinar Series: LIMES
LOD2 Webinar Series: LIMESLOD2 Webinar Series: LIMES
LOD2 Webinar Series: LIMES
 
Limes webinar
Limes webinarLimes webinar
Limes webinar
 
Work Package 3 - Month 6 by Christian Morbidoni
Work Package 3 - Month 6 by Christian MorbidoniWork Package 3 - Month 6 by Christian Morbidoni
Work Package 3 - Month 6 by Christian Morbidoni
 
NoTube: Models & Semantics
NoTube: Models & SemanticsNoTube: Models & Semantics
NoTube: Models & Semantics
 
LOD2 - Creating Knowledge out of Interlinked Data - General Presentation
LOD2 - Creating Knowledge out of Interlinked Data - General PresentationLOD2 - Creating Knowledge out of Interlinked Data - General Presentation
LOD2 - Creating Knowledge out of Interlinked Data - General Presentation
 
WP3 Further specification of Functionality and Interoperability - Gradmann / ...
WP3 Further specification of Functionality and Interoperability - Gradmann / ...WP3 Further specification of Functionality and Interoperability - Gradmann / ...
WP3 Further specification of Functionality and Interoperability - Gradmann / ...
 
06 dm2 e_pisa-wp2-no-anim
06 dm2 e_pisa-wp2-no-anim06 dm2 e_pisa-wp2-no-anim
06 dm2 e_pisa-wp2-no-anim
 
Linked Open Data Visualization
Linked Open Data VisualizationLinked Open Data Visualization
Linked Open Data Visualization
 
Linked Open Data stuff
Linked Open Data stuffLinked Open Data stuff
Linked Open Data stuff
 
Work Package 2 - Month 6 by Hannes Mühleisen
Work Package 2 - Month 6 by Hannes MühleisenWork Package 2 - Month 6 by Hannes Mühleisen
Work Package 2 - Month 6 by Hannes Mühleisen
 
Research Object Composer: A Tool for Publishing Complex Data Objects in the C...
Research Object Composer: A Tool for Publishing Complex Data Objects in the C...Research Object Composer: A Tool for Publishing Complex Data Objects in the C...
Research Object Composer: A Tool for Publishing Complex Data Objects in the C...
 

Más de LOD2 Creating Knowledge out of Interlinked Data

Más de LOD2 Creating Knowledge out of Interlinked Data (16)

LOD2 Webinar Series: Virtuoso 7
LOD2 Webinar Series: Virtuoso 7LOD2 Webinar Series: Virtuoso 7
LOD2 Webinar Series: Virtuoso 7
 
LOD2 Webinar Series: DBpedia Spotlight
LOD2 Webinar Series: DBpedia SpotlightLOD2 Webinar Series: DBpedia Spotlight
LOD2 Webinar Series: DBpedia Spotlight
 
LOD2 Webinar Series: publicdata.eu and CKAN
LOD2 Webinar Series: publicdata.eu and CKANLOD2 Webinar Series: publicdata.eu and CKAN
LOD2 Webinar Series: publicdata.eu and CKAN
 
LOD2 Webinar Series: LOD2 in information and publishing industry
LOD2 Webinar Series: LOD2 in information and publishing industryLOD2 Webinar Series: LOD2 in information and publishing industry
LOD2 Webinar Series: LOD2 in information and publishing industry
 
LOD2 General Presentation 2012
LOD2 General Presentation 2012LOD2 General Presentation 2012
LOD2 General Presentation 2012
 
LOD2 Webinar Series: PoolParty
LOD2 Webinar Series: PoolPartyLOD2 Webinar Series: PoolParty
LOD2 Webinar Series: PoolParty
 
LOD2 Plenary Vienna 2012: WP12 - Project Management
LOD2 Plenary Vienna 2012: WP12 - Project ManagementLOD2 Plenary Vienna 2012: WP12 - Project Management
LOD2 Plenary Vienna 2012: WP12 - Project Management
 
LOD2 Plenary Vienna 2012: WP10 - Training, Dissemination, Community Building,...
LOD2 Plenary Vienna 2012: WP10 - Training, Dissemination, Community Building,...LOD2 Plenary Vienna 2012: WP10 - Training, Dissemination, Community Building,...
LOD2 Plenary Vienna 2012: WP10 - Training, Dissemination, Community Building,...
 
LOD2 Plenary Vienna 2012: WP9A - LOD for a Distributed Marketplace for Public...
LOD2 Plenary Vienna 2012: WP9A - LOD for a Distributed Marketplace for Public...LOD2 Plenary Vienna 2012: WP9A - LOD for a Distributed Marketplace for Public...
LOD2 Plenary Vienna 2012: WP9A - LOD for a Distributed Marketplace for Public...
 
LOD2 Plenary Vienna 2012: WP9 publicdata.eu – Publishing Governmental Informa...
LOD2 Plenary Vienna 2012: WP9 publicdata.eu – Publishing Governmental Informa...LOD2 Plenary Vienna 2012: WP9 publicdata.eu – Publishing Governmental Informa...
LOD2 Plenary Vienna 2012: WP9 publicdata.eu – Publishing Governmental Informa...
 
LOD2 Plenary Vienna 2012: WP8: Linked Open Data for Enterprise Data Web
LOD2 Plenary Vienna 2012: WP8: Linked Open Data for Enterprise Data WebLOD2 Plenary Vienna 2012: WP8: Linked Open Data for Enterprise Data Web
LOD2 Plenary Vienna 2012: WP8: Linked Open Data for Enterprise Data Web
 
LOD2 Plenary Vienna 2012: WP7 - Linked Open Data for Media and Publishing
LOD2 Plenary Vienna 2012: WP7 - Linked Open Data for Media and Publishing LOD2 Plenary Vienna 2012: WP7 - Linked Open Data for Media and Publishing
LOD2 Plenary Vienna 2012: WP7 - Linked Open Data for Media and Publishing
 
LOD2 Plenary Vienna 2012: WP6 - Interfaces, Integration & LOD2 Stack
LOD2 Plenary Vienna 2012: WP6 - Interfaces, Integration & LOD2 StackLOD2 Plenary Vienna 2012: WP6 - Interfaces, Integration & LOD2 Stack
LOD2 Plenary Vienna 2012: WP6 - Interfaces, Integration & LOD2 Stack
 
LOD2 Plenary Vienna 2012: WP5 - Linked Data Browsing, Visualization and Autho...
LOD2 Plenary Vienna 2012: WP5 - Linked Data Browsing, Visualization and Autho...LOD2 Plenary Vienna 2012: WP5 - Linked Data Browsing, Visualization and Autho...
LOD2 Plenary Vienna 2012: WP5 - Linked Data Browsing, Visualization and Autho...
 
LOD2 Webinar Series: OntoWiki
LOD2 Webinar Series: OntoWikiLOD2 Webinar Series: OntoWiki
LOD2 Webinar Series: OntoWiki
 
LOD2 Plenary Meeting 2011: Institute Mihajlo Pupin – Partner Introduction
LOD2 Plenary Meeting 2011: Institute Mihajlo Pupin – Partner IntroductionLOD2 Plenary Meeting 2011: Institute Mihajlo Pupin – Partner Introduction
LOD2 Plenary Meeting 2011: Institute Mihajlo Pupin – Partner Introduction
 

Último

Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationnomboosow
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docxPoojaSen20
 
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...Sapna Thakur
 
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...fonyou31
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...Pooja Nehwal
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 

Último (20)

Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communication
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docx
 
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
 
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...Russian Call Girls in Andheri Airport Mumbai WhatsApp  9167673311 💞 Full Nigh...
Russian Call Girls in Andheri Airport Mumbai WhatsApp 9167673311 💞 Full Nigh...
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 

LOD2 Plenary Vienna 2012: WP3 - Knowledge Base Creation, Enrichment and Repair

  • 1. Creating Knowledge out of Interlinked Data LOD2 Plenary Vienna – 2012/03/21 – Page 1 http://lod2.eu Plenary Vienna – State-of-Play WP3: Knowledge Base Creation, Enrichment and Repair Jens Lehmann AKSW, Universität Leipzig LOD2 Presentation . 02.09.2010 . Page http://lod2.eu
  • 2. LOD2 Plenary Vienna – 2012/03/21 – Page 2 http://lod2.eu WP3 High Level Objectives Inc 8 Tasks, 9 Partners, 14 Deliverables, 20+ tools ons ist enc → lightweight integration via LOD2 stack Modelling y Problems Repair Mutual Refinement Cycle (with Refactoring optional Extraction phase) Structured Semi- Property- structured Axioms Extraction Definitions Enrichment Un- Data structured Summary
  • 3. LOD2 Plenary Vienna – 2012/03/21 – Page 3 http://lod2.eu WP3 Task 3.1 ● Provenance-Aware Extraction of Linked Data from Existing Structured Formats ● Partners: FUB, ULEI, OpenLink, Exalead ● Development and Support of RDB2RDF mapping standards (R2RML) ● Re-Use of existing tools/frameworks: ● D2R (FUB) ● Triplify (ULEI) ● Virtuoso Sponger and RDF Views (OpenLink) ● New Tool: Sparqlify ● Deliverables: State-of-the Art Report (M6), D2R release (M20), Triplify release (M20)
  • 4. LOD2 Plenary Vienna – 2012/03/21 – Page 4 http://lod2.eu WP3 Task 3.1 – Progress / Planned ✔ D3.1.1: state of the art in knowledge extraction from structured sources ● 200+ tools collected at http://data.lod2.eu/2011/tools/ ● http://en.wikipedia.org/wiki/Knowledge_extraction (2000 views/month) ✔ D3.1.2: D2R Server MetaData Extension (allows adding licencing and provenance output to D2R server) ● D3.1.3: Sparqlify: ● 1-1 SPARQL-to-SQL-Rewriting ● DB-Planner has Full Control ● Easy to Configure ● Tested on LinkedGeoData ● Release in 1-2 months D2R Architecture
  • 5. LOD2 Plenary Vienna – 2012/03/21 – Page 5 http://lod2.eu WP3 Task 3.2 • Provenance-Aware Extraction of Linked Data from Unstructured and Semi-Structured Sources (plain text, HTML, wikis, blogs) • Partners: FUB, ULEI, OpenLink, Exalead, Zemanta, KAIST, UEP • NLP techniques / text understanding • Draws on existing tools: • Stanford Parser, ASV toolkit, Ontos API (all external), Zemanta • DBpedia (FUB, ULEI, OpenLink) • Deliverables: NLP2RDF release (M8), DBpedia Live (M8), DBpedia Framework Extension (M27) • Other: DBpedia Spotlight Release, DBpedia I18n committee founded
  • 6. LOD2 Plenary Vienna – 2012/03/21 – Page 6 http://lod2.eu WP3 Task 3.2 – NLP2RDF + NIF • NLP Interchange Format (NIF) is an RDF/OWL-based format to combine and chain NLP tools • NLP2RDF (http://nlp2rdf.org) is a project providing: • Documentation and tutorials • Reference implementations of NIF • Collaboration and mailing lists • Roadmap of NIF in LOD2: • Integration of Zemanta API (Task 3.7) • BoA – tool for automated hypernym discovery and entity classification to ad hoc classes, using Wikipedia and Wordnet • Ex – tool for information extraction from heterogeneous web resources • MultiLingual Extraction (Task 3.6)
  • 7. LOD2 Plenary Vienna – 2012/03/21 – Page 7 http://lod2.eu WP3 Task 3.2 – NLP2RDF + NIF
  • 8. LOD2 Plenary Vienna – 2012/03/21 – Page 8 http://lod2.eu WP3 Task 3.2 – DBpedia Live Motivation • Wikipedia 7th most popular website (according to alexa.com) • Covers a variety of disciplines • DBpedia (from FUB, ULEI, OpenLink): ☺ Extracts structured data from Wikipedia ☺ Interlinks with other knowledge bases ☺ Can answer complex queries ☺ Is used in many applications / companies Θ Requires manual effort to create a release Θ Data is often several months old DBpedia Live Synchronisation with Wikipedia
  • 9. LOD2 Plenary Vienna – 2012/03/21 – Page 9 http://lod2.eu WP3 Task 3.2 – DBpedia Live Architecture • Works on live stream of updates provided by Wikipedia • Handles live changes of ontology and mappings (explained later) • Provides public endpoint at http://live.dbpedia.org/sparql and mirrors
  • 10. LOD2 Plenary Vienna – 2012/03/21 – Page 10 http://lod2.eu WP3 Task 3.3 • Knowledge Base Schema Enrichment • Partners: ULEI • Suggests OWL Schema Axioms to Knowlege Base Maintainers (Definitions, Super Classes, Disjointness, Domain, Range, …) • Extends DL-Learner (ULEI) machine learning framework • Tight coupling of Tasks 3.3 (Enrichment) and 3.4 (Repair): • Both will be integrated in the ORE tool • Iteration of Repair and Enrichment to improve quality • Adapts existing approaches to work with very large Linked Data knowledge bases (incl. SPARQL support)
  • 11. LOD2 Plenary Vienna – 2012/03/21 – Page 11 http://lod2.eu WP3 Task 3.3: Learning Schema Axioms Deliverables: D3.3.1 Enrichment Algorithms (M12), D3.3.2 Enrichment User Interfaces (M24), D3.3.3 Evaluation (M36)
  • 12. LOD2 Plenary Vienna – 2012/03/21 – Page 12 http://lod2.eu WP3 Task 3.4 • Knowledge Base Repair • Partners: ULEI, NUIG • Fix inconsistent knowledge bases, unsatisfiable classes, (some) modelling errors, (some) reasoning performance problems • Draws on a lot of existing work in ontology debugging and extends it to knowledge bases in the LOD cloud • Related to Task 4.3 (Linked Data Quality Assessment) • Result: ORE tool (together with Task 3.3) • Deliverables: Report on Modelling Errors/Problems (M6), 1st ORE Release (M28), 2nd ORE Release (M40)
  • 13. LOD2 Plenary Vienna – 2012/03/21 – Page 13 http://lod2.eu WP3 Task 3.4 - Progress • ORE (ontology repair and enrichment) tool started: • Code: http://code.google.com/p/ore • General Information: http://ore-tool.net • Web Prototype: http://web.ore-tool.net (preliminary) • Included in LOD2 stack ✔ Deliverable 3.4.1 (State of the Art on Modelling Problems) completed: • Comprehensive overview on modelling problems, syntactical and semantical errors • One of the conclusions: many tools available but scalability still an issue • ORE will focus on fragment extraction, incremental reasoning, high reuse of existing tools and libraries • work on algorithms for supporting debugging SPARQL endpoints
  • 14. LOD2 Plenary Vienna – 2012/03/21 – Page 14 http://lod2.eu WP3 Task 3.4a • Knowledge base repair/refactoring based on naming/content patterns • Partners: UEP • Started February 2012 as extension to T3.4 (Knowledge base repair from logical point of view) • Long-term goal is to bring the outcomes of the state-of-the-art ontology patterns research to the LOD2 Stack • Result: a component for ORE allowing to detect taxonomic naming → discussion in breakout session • (Anti-)patterns and suggested repairs will be developed until M24 • long term, prominent linked data vocabularies will be analyzed and mapped on ontology (content) design patterns • Will lead to improvement in ontology repair and enrichment (WP3) as well as in ontology matching & instance linking (WP4)
  • 15. LOD2 Plenary Vienna – 2012/03/21 – Page 15 http://lod2.eu WP3 Task 3.5 • Web Linkage Validator • Partners: NUIG, Exalead • companion tool for unsupervised interlinking of data on the Semantic Web • Dataset owners or authors utilise the tool by submitting their data for internal and external linkage analysis • analytics will be used to perform recommendations and suggestions for ways in which they may improve the linkage of their data, e.g. suggest to add further properties, more specific property values, better specify classes/properties • Deliverables: Initial Release (M18), LOD2 Stack Component Release (M28)
  • 16. LOD2 Plenary Vienna – 2012/03/21 – Page 16 http://lod2.eu WP3 Task 3.5
  • 17. LOD2 Plenary Vienna – 2012/03/21 – Page 17 http://lod2.eu WP3 Task 3.6 • Multi-Lingual Provenance-Aware Linked Data Extraction • Partners: IMP • Information retrieval: find documents using appropriate keywords (e.g. search engines: Google, Yahoo!, Baidu, Bing, etc.) • Functionality not supported: find documents using a natural language document instead of using keywords • Possible applications: Patent search (patent attorneys); Case search (lawyers); Anamnesis search (physicians); Paper search (researchers) • The corresponding NLP technique will enable: • Processing of documents in multiple languages • Extraction of a vocabulary of concepts (words, phrases) specific for each class of documents • Representation of domain specific vocabularies and links to related documents (based on NIF format)
  • 18. LOD2 Plenary Vienna – 2012/03/21 – Page 18 http://lod2.eu WP3 Task 3.6 • Re-Uses many LOD2 stack components • NLP technique for the structured representation of natural language documents: ✔ Representation of natural language documents in structured form (words, phrases, sentences, paragraphs, documents) • Multi-lingual support based on UTF-8 format – ongoing activity • Creation of domain specific vocabularies based on classified documents – not started yet • Searching for similar documents based on domain specific concepts found in given document – not started yet • Sorting found documents according to similarity – not started yet • Deliverables: D3.6 Multi-Lingual Support for Linked Data Extraction (M30)
  • 19. LOD2 Plenary Vienna – 2012/03/21 – Page 19 http://lod2.eu WP3 Task 3.7 • Web Scale Link and Text Mining • Partners: ZEM • Gathering shallow semantic data about new entities – new knowledge about popular topics (not yet curated in LOD) • Contributes to WP3 by creating new LOD datasets • Extraction of new entities from blogs worldwide • Creation of lexicons for new entity types to be used in named entity extraction engines • Integration of new LOD datasets in Zemanta recommendation engine • Gain market advantage • Improved recommendations for bloggers and Zemanta free API users • Deliverables: D3.7.1 Shallow information extraction from blogs (M20), D3.7.2 Improved entity recommender engine (M36)
  • 20. LOD2 Plenary Vienna – 2012/03/21 – Page 20 http://lod2.eu Thanks for your attention! Project: http://lod2.eu Organisation: http://uni-leipzig.de, http://aksw.org Presenter: http://jens-lehmann.org