Transcript Semantic Web Agents: Hope or Hype

Semantic Web Agents:
Hope or Hype
Nicholas Gibbins
School of Electronics and Computer Science
University of Southampton
The Cynic’s View
The Semantic Web and agent technologies
are just old-fashioned artificial intelligence.
Artificial intelligence hasn’t delivered on its
previous promises, so why should it now?
What is the Semantic Web?
The Semantic Web is an extension of the
current Web in which information is given a
well-defined meaning, better enabling
computers and people to work in cooperation.
It is the idea of having data on the Web
defined and linked in a way that it can be used
for more effective discovery, automation,
integration and reuse across various
applications.
The Web can reach its full potential if it
becomes a place where data can be
processed by automated tools as well as
people.
W3C Activity Statement
Example: Scientific American article
2001-05
The Semantic Web
dc:title
akt:publishedIn
dc:date
dc:creator
vcard:fn
dc:creator
vcard:fn
dc:creator
vcard:fn
Tim Berners-Lee
James Hendler
Ora Lassila
dc:title
Scientific American
Relation and object types are
defined in a machine-understandable
form – an ontology
The Semantic Web layer cake
User Interface and Applications
Trust
Attribution
Rules
RDF Schema
RDF
Explanation
Ontologies +
Inference
Metadata
XML + Namespaces
URI
Encryption
OWL
SPARQL
(queries)
Signature
Proof
Standard syntax
Unicode
Identity
Visibility
The Semantic Web Hype Cycle
Semantic Web
c. 2004
Technology Peak of Inflated Trough of
Slope of
Trigger
Expectation Disillusionment Enlightenment
Plateau of
Productivity
Maturity
Gartner
Which Semantic Web?
Semantic Web as the Annotated Web
∙ Enrich existing web pages with annotations
∙ Classify web pages
∙ Use natural language techniques to extract
information from web pages
∙ Annotations enable enhanced browsing and
searching
∙ (but NLP is hard)
Which Semantic Web?
Semantic Web as the Web of Data
∙ Expose existing databases in a common format
∙ Express database schemas in a machineunderstandable form
∙ Common format allows the integration of data in
unexpected ways
∙ Machine-understandable schemas allow reasoning
about data
∙ (make the most of the structure you already have)
Rocket Science (not)
Is this rocket science? Well, not really. The Semantic Web,
like the World Wide Web, is just taking well established
ideas, and making them work interoperably over the
Internet. This is done with standards, which is what the
World Wide Web Consortium is all about. We are not
inventing relational models for data, or query systems or rulebased systems. We are just webizing them. We are just
allowing them to work together in a decentralized system without a human having to custom handcraft every
connection.
Tim Berners-Lee, Business Case for the Semantic Web,
http://www.w3.org/DesignIssues/Business
e-Science and the Semantic Web
∙ e-Science characterised as:
∙
∙
∙
∙
Large-scale science
Distributed global collaborations
Very large data collections
Very large scale computing resources
∙ Data integration will be a major issue
∙ Capture, publish, reuse data
∙ Agreed vocabularies for data exchange
∙ Improving the information
environment for chemists –
both within and beyond the lab
∙ Supporting chemists in the
preparation, execution, analysis
and dissemination of their work
http://www.smarttea.org/
Data Capture: The Lab Notebook
Ingredient List
Fluorinated biphenyl
Br11OCB
Potassium Carbonate
Butanone
Dissolve 4flourinated
biphenyl in
butanone
0.9 g
1.59 g
2.07 g
40 ml
Add
Add K2CO3
powder
Add
0.9031
Heat at reflux
for 1.5 hours
Reflux
grammes
Weigh
Butanone dried via silica column and
measured into 100ml RB flask.
Used 1ml extra solvent to wash out
container.
Sample of 4flourinated
biphenyl
Annotate
Add
1
1
2
2
Add
1
3
Reflux
text
Annotate
Butanone
Sample of
K2CO3
Powder
Measure
Weigh
text
40
Started reflux at 13.30. (Had to
change heater stirrer) Only reflux
for 45min, next step 14:15.
ml
2.0719
g
Publish and Reuse
http://ecrystals.chem.soton.ac.uk
Exchange Vocabularies
∙ BioPax Ontology (biological pathways)
∙ Metabolic and signalling pathways, molecular
interactions
∙ Gene Ontology (genes and gene products)
∙ Molecular function, cellular component, biological
process
∙ NCI Cancer Ontology
∙ Diseases, drugs, anatomy, genes
(and many others from other disciplines)
What are Agents?
∙ Many definitions of agent
∙
∙
∙
∙
Mobile agents
Collaborative agents
Social agents
Interface agents
∙ Three broad perspectives:
∙ Agents as design metaphor
∙ Agents as technology source
∙ Agents as simulation
Agent Based Computing
∙ Societies of components, owned by different
organisations
∙ Components provide services to each other
∙ Computing as a social activity
∙
∙
∙
∙
Workflows and Planning
Coordination, Collaboration and Negotiation
Markets and auctions
Models of trust and reputation
∙ Managing the distributed processing of data
Visibility
The Agent Hype Cycle
Agents
c. 1995
Agents
c. 2005
Technology Peak of Inflated Trough of
Slope of
Trigger
Expectation Disillusionment Enlightenment
Plateau of
Productivity
Maturity
What’s different this time?
∙ First agent wave assumed that a special
agent infrastructure was needed
∙ Hindered integration with existing systems
∙ Several high-profile failures in the marketplace
∙ Second agent wave is building on existing
technologies such as Web Services
∙ Incremental approach that integrates existing
systems
∙ Can be aligned with related work on Grid
Computing
Grid Computing
∙ e-Science applications typically have very high
computational requirements
∙ Grid Computing provides an infrastructure for
∙ Flexible, secure, coordinated resource sharing
∙ Dynamic collections of individuals, institutions and
resources
∙ Virtual organisations
∙ Workflow management
∙ Social computing, in effect
Video
Simulation
Diffractometer
Properties
Analysis
Structures
Database
X-Ray
e-Lab
Properties
e-Lab
Grid Middleware
http://www.combechem.org/
http://www.mygrid.org.uk
The Next Generation Grid
“The ongoing convergence between Grids, Web Services
and the Semantic Web is a fundamental step towards the
realisation of a common service-oriented architecture
empowering people to create, provide, access and use a
variety of intelligent services, anywhere, anytime, in a
secure, cost-effective and trustworthy way.”
Next Generation Grids 2
Requirements and Options for
European Grids Research 2005-2010 and Beyond
EU Expert Group Report July 2004
The Semantic Grid
∙ Grid Computing + Semantic Web
∙ Information and services are given a welldefined meaning
∙ Uses SW technologies – OWL, RDF, etc
∙ Ontologies for describing services
∙ Better enables computers and people
to work in cooperation
∙ Requires coordination and planning capabilities
found in agent technologies
Hope or Hype?
∙ Web Services and Grid Computing are
already a reality
∙ The Semantic Web is being used in largescale e-Science applications
∙ Agent technology is approaching maturity,
and offers management of rich patterns of
interaction in service-oriented systems
Thank you!