Download Slides - Electronics and Computer Science

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Data analysis wikipedia , lookup

Renormalization group wikipedia , lookup

Neuroinformatics wikipedia , lookup

Transcript
Why I Find The Semantic Web
Interesting
Hugh Glaser
DSSE Seminar 1/11/2
Semantic Web
• Definition: The Semantic Web is the abstract representation of
data on the World Wide Web, based on the RDF standards and
other standards to be defined. It is being developed by the W3C,
in collaboration with a large number of researchers and
industrial partners.
• "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." -- Tim BernersLee, James Hendler, Ora Lassila, The Semantic Web, Scientific
American, May 2001
http://www.w3.org/2001/sw/
Semantic Web Architecture
Advanced Knowledge Technologies
• EPSRC-funded IRC (Interdisciplinary
Research Centre)
• six years
• quite a bit of money
• Southampton lead, OU, Sheffield
Edinburgh, Aberdeen
• http://www.aktors.org/
• Semantic Web v. Engineering Support
Some Specific Challenges
•
•
•
•
Scale, scale and more scale
Information Acquisition
Co-Reference Analysis
Component Definition & Architecture
Information Acquisition
•
•
•
•
•
•
•
We need Metadata on documents
One day it will be created at source
Until then it needs to be extracted
Natural Language Processing?
To explore issues now, we need something now
Using DOME and other techniques
www.hyphen.info - orders of magnitude bigger
than anything else
Co-Reference Analysis 1
• Large scale means multiple resources
• How do we know that Hugh Glaser in the
RAE data is Hugh Glaser in ECS and Hugh
Glaser in Southampton, …?
• Even University of Southampton in the
RAE data is the same as www.soton.ac.uk?
Co-Reference Analysis 2
• Some techniques
– Gazetteer
– COP (Community of Practice)
– Fancy statistical methods
• How do they get used
• And cast as a service
• Then, how do we represent the knowledge?
– (Is this the symbol grounding problem?)
Component Definition &
Architecture
• Concept Diagram (text)
Taxono my
Taxono my
Taxono my
Conclusions
• A world of problems on a grand scale
• Plenty of room for pragmatism & fun
• Need many specialists
–
–
–
–
–
–
–
NLP
AI
Stats
DB
Business Process Modelling
…
Computer Science
• And I didn’t mention the Grid or Agents!