3. Motivation
The Semantic Web should:
Facilitate learning from the Web.
Facilitate reuse of learning outcomes.
Hypothesis :
Learning from data annotated with semantic
mark-up should outperform learning from
traditional (HTML) Web.
Goals:
The learned model should be expressed in a
Semantic Web Language.
Such a learned model should be re-usable across
domains and applications.
4. Preliminary Experiments
Compare performance of learning from plain
text and from semantic meta-data.
Using traditional ML algorithms as baseline
approach:
Naïve Bayes
K-Nearest Neighbour
Explore application of more knowledge
intensive approaches, such as ILP (Progol).
An Empirical Investigation of Learning From the Semantic Web, Pete Edwards,
Gunnar AA. Grimnes and Alun Preece – Presented at Semantic Web Mining
Workshop at ECML/PKDD, Helsinki, 2002
5. Issues
Datasets in a Semantic Web language were
very hard to come by.
We used two datasets:
ITTalks (Seminars described using HTML vs.
DAML+OIL).
Citeseer (Full text of Academic Papers vs. BibTex
converted to RDF).
How does RDF map to an instance
representation suitable for learning?
6. Results
Largely negative.
K Nearest Neighbour on plain-text had best accuracy.
… but: 10 lines of RDF vs. 6000 words of full-text paper.
Reasons for failure:
Shallow and artificial RDF.
Statistical methods used.
Progol results were the most interesting:
% Classifying Machine Learning papers:
inClass(A) :- publisher(A,'Morgan Kaufmann'),
booktitleword(A,learning).
7. Agentcities & the Evening Scenario
EU funded – 5th F.W.
In Aberdeen since
January’02.
WeatherAgent
online since
February’02.
Evening Scenario
City Nodes
Tourist Information
Recommendations
The fun has just
started:
OpenNET
8. GraniteNights
Raison d’être:
Agentcities Agent Technology Competition.
Need a Semantic Web framework for
learning user profiles.
Bring together different people/research
areas in the department: agents, learning,
scheduling, constraints, etc.
Proof that RDF is usable!
GraniteNights - A Multi-Agent Visit Scheduler Utilising Semantic Web Technology,
Gunnar AA. Grimnes, Stuart Chalmers, Pete Edwards and Alun Preece
Submitted to CIA2003
11. Query By Example
RDQL too complicated to write by hand.
Query by example is very intuitive.
Internal conversion to RDQL.
Could be “smarter” than RDQL.
<q:Query> SELECT ?x WHERE (?x, ?y, ?z),
<q:template>
<akt:Academic> ( ?x, <rdf # type>, <akt # Academic> ),
<akt:family-name> ( ?x, <akt # family-name>, "Brown" )
Brown
</akt:family-name>
</akt:Academic>
</q:template>
</q:Query>
14. GraniteNights Profiling II
Current implementation:
Most frequently specified constraint.
Possible improvements:
Super/Sub-class inference in the ontology,
i.e. Flowers and Hobgoblin are both sub-
classes of Real Ale.
Combination of constraints important,
i.e.Pete likes Lager when eating Curry, but
Ale for his occasional pub-visit.
Requires more sophisticated techniques
than counting.
15. The Future
User modelling in a broader scope:
User roles, commitments etc.
Learning from RDF:
Generalisation.
Case-based reasoning.
RDF as model language.
Learning Knowledge Rich User Models from the Semantic Web, Gunnar AA. Grimnes
To appear in Doctoral Consortium, User Modeling 2003, Pittsburgh, July 2003.