New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
LOD2 Webinar Series FOX
1. Creating Knowledge out of Interlinked Data
LOD2 Webinar . 29.11.2011 . Page 1
http://lod2.eu
2. LOD2 is a large-scale integrating project co-funded by the European Commission
within the FP7 Information and Communication Technologies Work Programme.
This 4-year project comprises leading Linked Open Data technology
researchers, companies, and service providers. Coming from across 12 countries
the partners are coordinated by the Agile Knowledge Engineering and Semantic
Web Research Group at the University of Leipzig, Germany.
LOD2 will integrate and syndicate Linked Data with existing large-scale
applications. The project shows the benefits in the scenarios of Media and
Publishing, Corporate Data intranets and eGovernment.
http://lod2.eu
3. Once per month the LOD2 webinar series offer a free webinar about
tools and services along the Linked Open Data Life Cycle.
Stay with us and learn more about
acquisition, editing, composing, connected applications – and finally
publishing Linked Open Data.
http://lod2.eu
5. Creating Know le dge
out of Interlinked Data
Motivation
• Steady growth but incomplete
• Structured data
•
Triplify, Sparqlify
• Semi-structured data
•
DBpedia
• Unstructured data
•
•
Make up 80% of the Web
Diverse solutions, yet low F-score even on non-noisy
data
• Solution: FOX
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 5
http://lod2.eu
6. Creating Know le dge
out of Interlinked Data
Insight
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 6
http://lod2.eu
7. Creating Know le dge
out of Interlinked Data
Insight
• Diversity of solutions to one problem
•
NER, KE, RE
• Each solution has its strengths and weakness
• Apply ensemble learning to
•
Combine the tools at hand
•
Compute better results
•
In our case, decision trees (v2)
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 7
http://lod2.eu
8. Creating Know le dge
out of Interlinked Data
Architecture
NER
Learning
KE
Orchestration
RE
Prediction
NED
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 8
http://lod2.eu
9. Creating Know le dge
out of Interlinked Data
Named Entity Disambiguation
• Use AGDISTIS Framework
http://aksw.org/projects/AGDISTIS
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 9
http://lod2.eu
10. Creating Know le dge
out of Interlinked Data
Implementation
• N3
• Input
• …
• Text
• HTML
• Execution
• URL
• Single tools (light)
• FOX Full
• Output
• JSON-LD
• Access
• RDF/XML
• REST
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 10
http://lod2.eu
11. Creating Know le dge
out of Interlinked Data
Evaluation (FOX)
MUC-7 Corpus
• 6013 locations
• 11093 organizations
• 5882 persons
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 11
http://lod2.eu
12. Creating Know le dge
out of Interlinked Data
Evaluation (AGDISTIS)
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 12
http://lod2.eu
13. Creating Know le dge
out of Interlinked Data
Demo
http://fox.aksw.org
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 13
http://lod2.eu
14. Creating Know le dge
out of Interlinked Data
FOX API Parameters
input : text or an url
type : { text | url }
task : { NER }
output : { JSONLD | N3 | N-TRIPLE | RDF/{ JSON |
XML | XML-ABBREV} | TURTLE }
returnHtml : { true | false }
foxlight : an implemented INER class name (e.g.
`org.aksw.fox.nertools.NEROpenNLP`) or `OFF`.
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 14
http://lod2.eu
15. Creating Know le dge
out of Interlinked Data
FOX API Parameters
curl -d type=text -d task=NER -d output=JSONLD --dataurlencode "input=The foundation of the University of
Leipzig in 1409 initiated the city's development into a
centre of German law and the publishing industry, and
towards being a location of the Reichsgericht (High
Court), and the German National Library (founded in
1912). The philosopher and mathematician Gottfried
Leibniz was born in Leipzig in 1646, and attended the
university from 1661-1666." -H "Content-Type:
application/x-www-form-urlencoded" <SERVICE_URI>
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 15
http://lod2.eu
17. Creating Know le dge
out of Interlinked Data
FOX Response
[
a scmsann:ORGANIZATION , ann:Annotation ;
scms:beginIndex "22"^^xsd:int ;
scms:endIndex "43"^^xsd:int ;
scms:means <http://dbpedia.org/resource/Leipzig_University> ;
scms:source <http://ns.aksw.org/scms/tools/fox> ;
ann:body "University of Leipzig"^^xsd:string
].
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 17
http://lod2.eu
18. Creating Know le dge
out of Interlinked Data
AGDISTIS API
curl --data-urlencode "text='The <entity>University of
Leipzig</entity> was visited by <entity>Barack
Obama</entity>.'" -d type='agdistis' <SERVICEURL>
[{"namedEntity":"Barack
Obama","start":42, "disambiguatedURL":"http://dbpedia
.org/resource/Barack_Obama","offset":12},{"namedEnti
ty":"University of
Leipzig","start":5,"disambiguatedURL":"http://dbpedia.
org/resource/Leipzig_University","offset":21}]
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 18
http://lod2.eu
19. Creating Know le dge
out of Interlinked Data
Conclusion and Future Work
•
> 90% F-score
•
Can be extended to cover other KE tasks (RE, POS, …)
•
Easy integration into semantic applications
•
More info at http://fox.aksw.org and
http://aksw.org/projects/agdistis
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 19
http://lod2.eu
20. Creating Know le dge
out of Interlinked Data
Thank you for your attention!
Axel Ngonga
http://aksw.org/AxelNgonga | http://fox.aksw.org | http://lod2.org
ngonga@informatik.uni-leipzig.de
Axel Ngonga – Federated Knowledge Extraction
30.01.2014
Page 20
http://lod2.eu