SlideShare a Scribd company logo
Civet
                          From content to Linked Open Data
                               Sebastian Ryszard Kruk, PhD
                                   Arkadiusz Kwoska




Friday, December 14, 12
how to
                                                      make text
              Current                                  better
                                                    understood by
               issues                                 machines


                                        CIVET
                                      - from text                Open
                                        to RDFa              Vocabulary
                                                              - publishing
         where to                                             dictionaries
            get
       vocabularies
       for machines




                                                           Where
                          Potential                      to go from
                          problems                          here



Friday, December 14, 12
Human
                                                                              text vs
                                                                             machines




                                                             plain text is
                                                              virtually
                                                             useless for
                                                              machines




source: http://www.flickr.com/photos/libaer2002/2398312710/
Friday, December 14, 12
Human                                          NLP and tags
                                                                   only lower the
                      text vs                                           order
                     machines                                     of magnitude of
                            continued                                the problem




                                                                        but not
                                                                       too many
                                                                        orders

source: http://www.flickr.com/photos/matthias_haas67/4200170217/
Friday, December 14, 12
Human                                                                  we are already
                                                                           pass retrieving the
      text vs                                                              low “hanging fruit”
     machines                                                                semantics from
            continued                                                          databases
                                                                but
                                                           there’s a lot
                                                             of human
                                                           knowledge in
                                                            just plain
                                                               text




source: http://www.flickr.com/photos/katrinlorenzen/5409008140
Friday, December 14, 12
how to
                                                      make text
              Current                                  better
                                                    understood by
               issues                                 machines


                                        CIVET
                                      - from text                Open
                                        to RDFa              Vocabulary
                                                              - publishing
         where to                                             dictionaries
            get
       vocabularies
       for machines




                                                           Where
                          Potential                      to go from
                          problems                          here



Friday, December 14, 12
Where to
     get LOD
     Vocabs ?




source:http://www.flickr.com/photos/bfurlong/2351689062/
Friday, December 14, 12
Where
   to get LOD
    Vocabs ?
            continued




Friday, December 14, 12
Where
   to get LOD
    Vocabs ?
            continued




Friday, December 14, 12
how to
                                                       make text
              Current                                   better
                                                     understood by
               issues                                  machines


                                        CIVET
                                      from text to                Open
                                         RDFa                 Vocabulary
                                                               - publishing
         where to                                              dictionaries
            get
       vocabularies
       for machines




                                                            Where
                          Potential                       to go from
                          problems                           here



Friday, December 14, 12
CIVET -
                                                          from text
                                                           to RDFa


source:http://www.flickr.com/photos/xjrlokix/3269530621/
Friday, December 14, 12
CIVET -
                                                               from text
                                                                to RDFa
                                                                 continued




source: http://www.flickr.com/photos/72213316@N00/3149423057/
Friday, December 14, 12
CIVET -
                          from text
                           to RDFa
                            continued




Friday, December 14, 12
Friday, December 14, 12
Friday, December 14, 12
Friday, December 14, 12
Friday, December 14, 12
how to
                                                      make text
              Current                                  better
                                                    understood by
               issues                                 machines


                                        CIVET
                                      - from text                Open
                                        to RDFa              Vocabulary
                                                              - publishing
         where to                                             dictionaries
            get
       vocabularies
       for machines




                                                           Where
                          Potential                      to go from
                          problems                          here



Friday, December 14, 12
OpenVocabulary:
       from legacy
  dictionaries to LOD




Friday, December 14, 12
how to
                                                      make text
              Current                                  better
                                                    understood by
               issues                                 machines


                                        CIVET
                                      - from text                Open
                                        to RDFa              Vocabulary
                                                              - publishing
         where to                                             dictionaries
            get
       vocabularies
       for machines




                                                           Where
                          Potential                      to go from
                          problems                          here



Friday, December 14, 12
Mind the hole ...




         Mind
       the hole


Friday, December 14, 12
Mind the
                                      hole
                                      continued

                working
               with text is
              sometimes           often,
                tricky           when you
                              deal with non-
                               English text




Friday, December 14, 12
Mind the
                hole
                   continued



                                    current
                                    meaning
           but they                discovery
        do not take            algorithms are still
         into account            questionable
        linked data  



Friday, December 14, 12
how to
                                                      make text
              Current                                  better
                                                    understood by
               issues                                 machines


                                        CIVET
                                      - from text                Open
                                        to RDFa              Vocabulary
                                                              - publishing
         where to                                             dictionaries
            get
       vocabularies
       for machines




                                                           Where
                          Potential                      to go from
                          problems                          here



Friday, December 14, 12
Where                      discovering
            to go from                       key
               here?                     meaningful
                                            facts


                            Improve,
                          improve,
                           improve ...
     quality and          meaning
    performance           discovery



Friday, December 14, 12
SemLib

       Where                                   recommendation
                                                   engine to
     to go from                  SemLib             utilize
        here?               annotation engine       results
              continued       for gathering
                          feedback discovering
                             key meaningful
                                  facts
           Validate,
          validate,                            with real
          validate ...                        users with
           results                               real
                                              problems

Friday, December 14, 12
Civet
                             From content to Linked Open Data
                                        http://civet.knowledgehives.com/
                Semantic tools for digital libraries a.k.a. SemLib is a 24th month R&D project supported by EU FP7
                 Theme: Research for SMEs (no. FP7-SME-2010-01-262301-SEMLIB) commenced in January 2011.
                                               More info at http://www.semlibproject.eu




Friday, December 14, 12

More Related Content

PPT
Perfume
PPTX
Perfumes ppt
PPTX
Vaccines
PDF
Relevancy and Context: The Key to Great Mobile Experiences
PPT
My Robot
PDF
Jana Diesner, "Words and Networks: Considering the Content of Text Data for N...
PDF
When machines think
PDF
IRJET- Virtual Vision for Blinds
Perfume
Perfumes ppt
Vaccines
Relevancy and Context: The Key to Great Mobile Experiences
My Robot
Jana Diesner, "Words and Networks: Considering the Content of Text Data for N...
When machines think
IRJET- Virtual Vision for Blinds

Similar to Civet - from Content to Linked Open Data (20)

PDF
Command, Goal Disambiguation, Introspection, and Instruction in Gesture-Free ...
PDF
Simulation Informatics
PDF
Fcv hum mach_perona
PPT
Pete^2 - research presentation wk7
PDF
Horstmann digital strategies_for_21st_century_libraries
PDF
Generator Tricks for Systems Programmers
PPTX
software-2.0.pptx
PDF
Cloud computing: evolution or redefinition
PDF
Artificial intelligence
PPT
Where are we going and how are we going to get there?
PDF
The Machine Stops: Where to from Here?
KEY
Designing the future
PPT
Ethics of AI
PDF
Electricity that loves
PDF
Generator Tricks for Systems Programmers, v2.0
PDF
FabLab Of Machines Makers and Inventors 1. Aufl. Edition Julia Walter-Herrman...
PDF
Machine Learning Lecture 1 - Introduction
PDF
LAB at Rockwellgroup: Presentation at Sparkfun, October 2012
PDF
SIKS SIREN 2010 poster
Command, Goal Disambiguation, Introspection, and Instruction in Gesture-Free ...
Simulation Informatics
Fcv hum mach_perona
Pete^2 - research presentation wk7
Horstmann digital strategies_for_21st_century_libraries
Generator Tricks for Systems Programmers
software-2.0.pptx
Cloud computing: evolution or redefinition
Artificial intelligence
Where are we going and how are we going to get there?
The Machine Stops: Where to from Here?
Designing the future
Ethics of AI
Electricity that loves
Generator Tricks for Systems Programmers, v2.0
FabLab Of Machines Makers and Inventors 1. Aufl. Edition Julia Walter-Herrman...
Machine Learning Lecture 1 - Introduction
LAB at Rockwellgroup: Presentation at Sparkfun, October 2012
SIKS SIREN 2010 poster
Ad

More from Knowledge Hives (6)

PDF
SemLib Final Conference
PDF
The Web: history - now - future
ZIP
Szukanie odpowiedzi: wyszukiwarki trzeciej generacji
ZIP
Znajdowanie odpowiedzi z wykorzystaniem serwisów społecznościowych
PDF
Wprowadzenie do Web 3.0
PDF
Tutorial on Semantic Digital Libraries at ICSD'09
SemLib Final Conference
The Web: history - now - future
Szukanie odpowiedzi: wyszukiwarki trzeciej generacji
Znajdowanie odpowiedzi z wykorzystaniem serwisów społecznościowych
Wprowadzenie do Web 3.0
Tutorial on Semantic Digital Libraries at ICSD'09
Ad

Recently uploaded (20)

PDF
CIFDAQ's Market Insight: SEC Turns Pro Crypto
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PDF
Chapter 3 Spatial Domain Image Processing.pdf
PDF
Spectral efficient network and resource selection model in 5G networks
PPTX
Effective Security Operations Center (SOC) A Modern, Strategic, and Threat-In...
PDF
Modernizing your data center with Dell and AMD
PDF
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
PDF
Bridging biosciences and deep learning for revolutionary discoveries: a compr...
PDF
Review of recent advances in non-invasive hemoglobin estimation
PDF
Approach and Philosophy of On baking technology
PDF
Agricultural_Statistics_at_a_Glance_2022_0.pdf
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
PPTX
A Presentation on Artificial Intelligence
PDF
Advanced methodologies resolving dimensionality complications for autism neur...
PPTX
Cloud computing and distributed systems.
PPT
Teaching material agriculture food technology
PDF
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
PDF
Encapsulation_ Review paper, used for researhc scholars
PDF
Empathic Computing: Creating Shared Understanding
PDF
Per capita expenditure prediction using model stacking based on satellite ima...
CIFDAQ's Market Insight: SEC Turns Pro Crypto
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
Chapter 3 Spatial Domain Image Processing.pdf
Spectral efficient network and resource selection model in 5G networks
Effective Security Operations Center (SOC) A Modern, Strategic, and Threat-In...
Modernizing your data center with Dell and AMD
How UI/UX Design Impacts User Retention in Mobile Apps.pdf
Bridging biosciences and deep learning for revolutionary discoveries: a compr...
Review of recent advances in non-invasive hemoglobin estimation
Approach and Philosophy of On baking technology
Agricultural_Statistics_at_a_Glance_2022_0.pdf
“AI and Expert System Decision Support & Business Intelligence Systems”
A Presentation on Artificial Intelligence
Advanced methodologies resolving dimensionality complications for autism neur...
Cloud computing and distributed systems.
Teaching material agriculture food technology
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
Encapsulation_ Review paper, used for researhc scholars
Empathic Computing: Creating Shared Understanding
Per capita expenditure prediction using model stacking based on satellite ima...

Civet - from Content to Linked Open Data

  • 1. Civet From content to Linked Open Data Sebastian Ryszard Kruk, PhD Arkadiusz Kwoska Friday, December 14, 12
  • 2. how to make text Current better understood by issues machines CIVET - from text Open to RDFa Vocabulary - publishing where to dictionaries get vocabularies for machines Where Potential to go from problems here Friday, December 14, 12
  • 3. Human text vs machines plain text is virtually useless for machines source: http://www.flickr.com/photos/libaer2002/2398312710/ Friday, December 14, 12
  • 4. Human NLP and tags only lower the text vs order machines of magnitude of continued the problem but not too many orders source: http://www.flickr.com/photos/matthias_haas67/4200170217/ Friday, December 14, 12
  • 5. Human we are already pass retrieving the text vs low “hanging fruit” machines semantics from continued databases but there’s a lot of human knowledge in just plain text source: http://www.flickr.com/photos/katrinlorenzen/5409008140 Friday, December 14, 12
  • 6. how to make text Current better understood by issues machines CIVET - from text Open to RDFa Vocabulary - publishing where to dictionaries get vocabularies for machines Where Potential to go from problems here Friday, December 14, 12
  • 7. Where to get LOD Vocabs ? source:http://www.flickr.com/photos/bfurlong/2351689062/ Friday, December 14, 12
  • 8. Where to get LOD Vocabs ? continued Friday, December 14, 12
  • 9. Where to get LOD Vocabs ? continued Friday, December 14, 12
  • 10. how to make text Current better understood by issues machines CIVET from text to Open RDFa Vocabulary - publishing where to dictionaries get vocabularies for machines Where Potential to go from problems here Friday, December 14, 12
  • 11. CIVET - from text to RDFa source:http://www.flickr.com/photos/xjrlokix/3269530621/ Friday, December 14, 12
  • 12. CIVET - from text to RDFa continued source: http://www.flickr.com/photos/72213316@N00/3149423057/ Friday, December 14, 12
  • 13. CIVET - from text to RDFa continued Friday, December 14, 12
  • 18. how to make text Current better understood by issues machines CIVET - from text Open to RDFa Vocabulary - publishing where to dictionaries get vocabularies for machines Where Potential to go from problems here Friday, December 14, 12
  • 19. OpenVocabulary: from legacy dictionaries to LOD Friday, December 14, 12
  • 20. how to make text Current better understood by issues machines CIVET - from text Open to RDFa Vocabulary - publishing where to dictionaries get vocabularies for machines Where Potential to go from problems here Friday, December 14, 12
  • 21. Mind the hole ... Mind the hole Friday, December 14, 12
  • 22. Mind the hole continued working with text is sometimes often, tricky when you deal with non- English text Friday, December 14, 12
  • 23. Mind the hole continued current meaning but they discovery do not take algorithms are still into account questionable linked data   Friday, December 14, 12
  • 24. how to make text Current better understood by issues machines CIVET - from text Open to RDFa Vocabulary - publishing where to dictionaries get vocabularies for machines Where Potential to go from problems here Friday, December 14, 12
  • 25. Where discovering to go from key here? meaningful facts Improve, improve, improve ... quality and meaning performance discovery Friday, December 14, 12
  • 26. SemLib Where recommendation engine to to go from SemLib utilize here? annotation engine results continued for gathering feedback discovering key meaningful facts Validate, validate, with real validate ... users with results real problems Friday, December 14, 12
  • 27. Civet From content to Linked Open Data http://civet.knowledgehives.com/ Semantic tools for digital libraries a.k.a. SemLib is a 24th month R&D project supported by EU FP7 Theme: Research for SMEs (no. FP7-SME-2010-01-262301-SEMLIB) commenced in January 2011. More info at http://www.semlibproject.eu Friday, December 14, 12