Page 1
Competence Center Case-Based Reasoning
CASE ACQUISITION FROM TEXT: ONTOLOGY-BASED INFORMATION
EXTRACTION WITH SCOOBIE FOR MYCBRThomas Roth-Berghofer, Benjamin Adrian, and Andreas Dengel
German Research Center for Artificial Intelligence DFKI GmbH
Donnerstag, 5. August 2010
Page 2
© 2
010
DFK
I CC
CBR
COMPETENCE CENTERCASE-BASED REASONING (CC CBR)
Klaus-Dieter Althoff
Thomas Roth-Berghofer
ArminStahl
Donnerstag, 5. August 2010
Page 3
© 2
010
DFK
I CC
CBR
COMPETENCE CENTERCASE-BASED REASONING (CC CBR)
Klaus-Dieter Althoff
Thomas Roth-Berghofer
ArminStahl
KerstinBach
RégisNewo
Donnerstag, 5. August 2010
Page 4
© 2
010
DFK
I CC
CBR
MOTIVATION
Donnerstag, 5. August 2010
Page 5
© 2
010
DFK
I CC
CBR
Ontologies
Ontology-based Information Extraction
RDFTexts
SCOOBIE
MOTIVATION
Donnerstag, 5. August 2010
Page 6
© 2
010
DFK
I CC
CBR
Ontologies
Ontology-based Information Extraction
RDFTexts
SCOOBIE
MOTIVATION
+
Donnerstag, 5. August 2010
Page 7
© 2
010
DFK
I CC
CBR
Ontologies
Ontology-based Information Extraction
RDFTexts
SCOOBIE
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
MOTIVATION
+
Donnerstag, 5. August 2010
Page 8
© 2
010
DFK
I CC
CBR
Ontologies
Ontology-based Information Extraction
RDFTexts
SCOOBIE
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
MOTIVATION
+
Donnerstag, 5. August 2010
Page 9
© 2
010
DFK
I CC
CBR
OVERVIEW
•Ontology-based Information Extraction with SCOOBIE
• Recap of myCBR
•myCBR+SCOOBIE
•Outlook and future work
Donnerstag, 5. August 2010
Page 10
© 2
010
DFK
I CC
CBR
SCOOBIE: ONTOLOGIE-BASED INFORMATION EXTRACTION
Donnerstag, 5. August 2010
Page 11
© 2
010
DFK
I CC
CBR
SCOOBIE
Ontologies
Ontology-based Information Extraction RDFTexts
Donnerstag, 5. August 2010
Page 12
© 2
010
DFK
I CC
CBR
EXTRACT PLAIN TEXT
Donnerstag, 5. August 2010
Page 13
© 2
010
DFK
I CC
CBR
EXTRACT TOKENS
Donnerstag, 5. August 2010
Page 14
© 2
010
DFK
I CC
CBR
EXTRACT TOKENS
Donnerstag, 5. August 2010
Page 15
© 2
010
DFK
I CC
CBR
EXTRACT TOKENS
Donnerstag, 5. August 2010
Page 16
© 2
010
DFK
I CC
CBR
RECOGNISE SYMBOLS
Donnerstag, 5. August 2010
Page 17
© 2
010
DFK
I CC
CBR
RECOGNISE SYMBOLS
Donnerstag, 5. August 2010
Page 18
© 2
010
DFK
I CC
CBR
RECOGNISE SYMBOLS
Donnerstag, 5. August 2010
Page 19
© 2
010
DFK
I CC
CBR
RECOGNISE SYMBOLS
Donnerstag, 5. August 2010
Page 20
© 2
010
DFK
I CC
CBR
Donnerstag, 5. August 2010
Page 21
© 2
010
DFK
I CC
CBR
RECAP: MOTIVATION FOR DEVELOPING
•Need for a freely available “out of the box” tool:
• compact and easy to use
• comfortable graphical user interface for
• defining case representations
•modeling knowledge-intensive similarity measures
• testing of retrieval functionality
• support for rapid prototyping
• adaptable & extendable
Donnerstag, 5. August 2010
Page 22
© 2
010
DFK
I CC
CBR
➜ ECCBR 2008
Armin Stahl and Thomas R. Roth-Berghofer. Rapid prototyping of CBR applications with the open source tool myCBR. In Ralph Bergmann and Klaus-Dieter Althoff, editors, Advances in Case-Based Reasoning. Springer Verlag, 2008.
Donnerstag, 5. August 2010
Page 23
© 2
010
DFK
I CC
CBR
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
MOTIVATION
Ontologies
Ontology-based Information Extraction
RDFTexts
SCOOBIE +
Donnerstag, 5. August 2010
Page 24
© 2
010
DFK
I CC
CBR
SEMANTIC WEB VISION
“The Semantic Web is an extension of the current Web in which information is given well-defined meaning, better enabling computers and people to work in cooperation.”
T. Berners-Lee, J. Hendler, O. Lassila, “The Semantic Web”, Scientific American, May 2001
Donnerstag, 5. August 2010
Page 25
© 2
010
DFK
I CC
CBR
SEMANTIC WEB VISION
“The Semantic Web is an extension of the current Web in which information is given well-defined meaning, better enabling computers and people to work in cooperation.”
T. Berners-Lee, J. Hendler, O. Lassila, “The Semantic Web”, Scientific American, May 2001
•Web of content
•Web pages linked by semantical relations
•Machines are able to process contents and links
Donnerstag, 5. August 2010
Page 26
© 2
010
DFK
I CC
CBR
SEMANTIC WEB VISION
“The Semantic Web is an extension of the current Web in which information is given well-defined meaning, better enabling computers and people to work in cooperation.”
T. Berners-Lee, J. Hendler, O. Lassila, “The Semantic Web”, Scientific American, May 2001
•Web of content
•Web pages linked by semantical relations
•Machines are able to process contents and links
• Web of content
•Web pages linked by semantical relations
•Machines are able to process contents and links
Donnerstag, 5. August 2010
Page 27
© 2
010
DFK
I CC
CBR
WEB OF DATA
• Characteristics:
• Expressed in RDF
• Identified by URIs
• Accessible via http
Donnerstag, 5. August 2010
Page 28
© 2
010
DFK
I CC
CBR
WEB OF TRIPLES
<rdf:Description rdf:about= "http://dbtropes.org/resource/Main/Ratatouille#Remy"> <does-not-like rdf:resource= "http://mycbr-project.net/models/Recipe#velveeta_cheese"/></rdf:Description>
Donnerstag, 5. August 2010
Page 29
© 2
010
DFK
I CC
CBR
WEB OF TRIPLES
<rdf:Description rdf:about= "http://dbtropes.org/resource/Main/Ratatouille#Remy"> <does-not-like rdf:resource= "http://mycbr-project.net/models/Recipe#velveeta_cheese"/></rdf:Description>
• Characteristics:
• Expressed in RDF
• Identified by URIs
• Accessible via http
Donnerstag, 5. August 2010
Page 30
© 2
010
DFK
I CC
CBR
WEB OF TRIPLES
<rdf:Description rdf:about= "http://dbtropes.org/resource/Main/Ratatouille#Remy"> <does-not-like rdf:resource= "http://mycbr-project.net/models/Recipe#velveeta_cheese"/></rdf:Description>
Donnerstag, 5. August 2010
Page 31
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Donnerstag, 5. August 2010
Page 32
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
<skos:Concept rdf:about="http://mycbr-project.net/models/Recipe#Shallots"> <skos:prefLabel> Shallots </skos:prefLabel> <rdf:type rdf:resource="ingredients_vegetables"/></skos:Concept> <skos:Concept rdf:about="http://mycbr-project.net/models/Recipe#Onions"> <skos:prefLabel> Onions </skos:prefLabel> <rdf:type rdf:resource="ingredients_vegetables"/> </skos:Concept>
Donnerstag, 5. August 2010
Page 33
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Donnerstag, 5. August 2010
Page 34
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
Donnerstag, 5. August 2010
Page 35
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Donnerstag, 5. August 2010
Page 36
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
<http://mycbr-project.net/models/Recipe#onions> owl:sameas <http://dbpedia.org/resource/Onion><http://mycbr-project.net/models/Recipe#green_fettuccine"> owl:sameas <http://dbpedia.org/resource/Fettucine><http://mycbr-project.net/models/Recipe#spinach_noodles"> owl:sameas <http://dbpedia.org/resource/Noodle>
Donnerstag, 5. August 2010
Page 37
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Donnerstag, 5. August 2010
Page 38
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Texts
Donnerstag, 5. August 2010
Page 39
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
Ontology-based Information Extraction
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Texts
Donnerstag, 5. August 2010
Page 40
© 2
010
DFK
I CC
CBR
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
Ontology-based Information Extraction
Case Base
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Texts
Donnerstag, 5. August 2010
Page 41
© 2
010
DFK
I CC
CBR
Jamendo
BBCProgrammes
Music-brainz
Magna-
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
riese
Geo-names
World Fact-
Euro-stat
flickrwrappr
Open Calais
SIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
QDOS
Pub Guide
Project Guten-berg
LIBRIS
ECS South-ampton
BBC Music
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
Ontology-based Information Extraction
Case Base
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Texts
Donnerstag, 5. August 2010
Page 42
© 2
010
DFK
I CC
CBR
Jamendo
BBCProgrammes
Music-brainz
Magna-
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
riese
Geo-names
World Fact-
Euro-stat
flickrwrappr
Open Calais
SIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
QDOS
Pub Guide
Project Guten-berg
LIBRIS
ECS South-ampton
BBC Music
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
Ontology-based Information Extraction
Case Base
myCBRAs of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Texts
Donnerstag, 5. August 2010
Page 43
© 2
010
DFK
I CC
CBR
Jamendo
BBCProgrammes
Music-brainz
Magna-
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
riese
Geo-names
World Fact-
Euro-stat
flickrwrappr
Open Calais
SIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
QDOS
Pub Guide
Project Guten-berg
LIBRIS
ECS South-ampton
BBC Music
USING LINKED DATA FOR CASE
GENERATIONLinkedCT
Reactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Case Model
Connection Model
Ontology-based Information Extraction
Case Base
myCBRAs of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Texts
Donnerstag, 5. August 2010
Page 44
© 2
010
DFK
I CC
CBR
• Improved UI based on Rich Client Platform• Use of Perspectives,
e.g., for text-to-case transformation via SCOOBIE• Plus SDK• Import of myCBR
2.6.x files•…
3
Donnerstag, 5. August 2010
Page 45
© 2
010
DFK
I CC
CBR
• Improved UI based on Rich Client Platform• Use of Perspectives,
e.g., for text-to-case transformation via SCOOBIE• Plus SDK• Import of myCBR
2.6.x files•…
3
Donnerstag, 5. August 2010
Page 46
© 2
010
DFK
I CC
CBR
PREVIEW
• Configuration of source XML file
• Assignment of attribute to XML path
• Copy or information extraction
3
Donnerstag, 5. August 2010
Page 47
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 48
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 49
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 50
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 51
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 52
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 53
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 54
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 55
© 2
010
DFK
I CC
CBR
PREVIEW3
Donnerstag, 5. August 2010
Page 56
© 2
010
DFK
I CC
CBR
OUTLOOK AND FUTURE WORK
Donnerstag, 5. August 2010
Page 57
© 2
010
DFK
I CC
CBR
LinkedCTReactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Jamendo
BBCProgrammes
Music-brainz
Magna-
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
riese
Geo-names
World Fact-
Euro-stat
flickrwrappr
Open Calais
SIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
QDOS
Pub Guide
Project Guten-berg
LIBRIS
ECS South-ampton
BBC Music
ITERATIVE IMPROVEMENT OF
CONNECTION MODEL
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Case Model
Connection Model
Ontology-based Information Extraction
Case Base
myCBR
Texts
Donnerstag, 5. August 2010
Page 58
© 2
010
DFK
I CC
CBR
LinkedCTReactome
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
ymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniR
PROSITE
Gene Ontology
PubChem
MGI
UniSTS
GEOSpecies
Magna-tune
LinkedMDB
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
W3CWordNet
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
RDF Book Mashup
Project Guten-berg
DBLPBerlin
Pisa
CiteSeer
RKBExplorer
RKBECS
South-ampton
Jamendo
BBCProgrammes
Music-brainz
Magna-
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
riese
Geo-names
World Fact-
Euro-stat
flickrwrappr
Open Calais
SIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
QDOS
Pub Guide
Project Guten-berg
LIBRIS
ECS South-ampton
BBC Music
ITERATIVE IMPROVEMENT OF
CONNECTION MODEL
As of July 2009
LinkedCTReactome
Taxonomy
KEGG
PubMed
GeneID
Pfam
UniProt
OMIM
PDB
SymbolChEBI
Daily Med
Disea-some
CAS
HGNC
InterPro
Drug Bank
UniParc
UniRef
ProDom
PROSITE
Gene Ontology
HomoloGene
PubChem
MGI
UniSTS
GEOSpecies
Jamendo
BBCProgrammes
Music-brainz
Magna-tune
BBCLater +TOTP
SurgeRadio
MySpaceWrapper
Audio-Scrobbler
LinkedMDB
BBCJohnPeel
BBCPlaycount
Data
Gov-Track
US Census Data
riese
Geo-names
lingvoj
World Fact-book
Euro-stat
flickrwrappr
Open Calais
RevyuSIOCSites
Doap-space
Flickrexporter
FOAFprofiles
CrunchBase
Sem-Web-
Central
Open-Guides
Wiki-company
QDOS
Pub Guide
RDF ohloh
W3CWordNet
OpenCyc
UMBEL
Yago
DBpedia
Freebase
Virtuoso Sponger
DBLPHannover
IRIT Toulouse
SWConference
Corpus
RDF Book Mashup
Project Guten-berg
DBLPBerlin
LAAS- CNRS
Buda-pestBME
IEEE
IBM
Resex
Pisa
New-castle
RAE 2001
CiteSeer
ACM
DBLP RKB
Explorer
eprints
LIBRIS
SemanticWeb.org
Eurécom
RKBECS
South-ampton
CORDIS
ReSIST ProjectWiki
NationalScience
Foundation
ECS South-ampton
LinkedGeoData
BBC Music
owl:sameas
Case Model
Connection Model
Ontology-based Information Extraction
Case Base
myCBR
Texts
Donnerstag, 5. August 2010
Page 59
Competence Center Case-Based Reasoning
CASE ACQUISITION FROM TEXT: ONTOLOGY-BASED INFORMATION
EXTRACTION WITH SCOOBIE FOR MYCBRThomas Roth-Berghofer, Benjamin Adrian, and Andreas Dengel
German Research Center for Artificial Intelligence DFKI GmbH
Thank you!
http://mycbr-project.net
http://www.dfki.de/~roth @thorob67
Donnerstag, 5. August 2010