Ontology Alignment
Ontologies are seen as the solution to data
heterogeneity on the web.
However, the available ontologies could themselves
introduce heterogeneity: given two ontologies, the same
entity can be given different names or simply be defined
in different ways, whereas both ontologies may express
the same knowledge but in different languages.
Semantic interoperability can be grounded in ontology
reconciliation.
The underlying problem, which we call the "ontology
alignment'' problem,
can be described as follows: given two ontologies each
describing a set of discrete entities (which can be
classes, properties, predicates, etc.), find the
relationships (e.g., equivalence or subsumption) that
hold between these entities.
Alignment results can further support visualization of
correspondences, transformation of one source into
another or formulation of bridge axioms between the
ontologies.
The alignment problem can be approached from various
standpoints and this fact is reflected in the variety of
alignment methods that have been proposed in the
literature. Many of them are rooted in the classical
problem of schema matching in the database area [4,7]
while others have been specifically designed to work
with ontologies [6,1].
Some methods rely on formal reasoning about the
structure of the entity descriptions [3],
others use a combination of similarity-based and
graph-based reasoning [5]
while a third, mainstream, group apply data analysis [8,9]
or machine learning techniques [2]
to make emerge good alignments. Our own system, OLA [12],
relies on the classical similarity-based paradigm for
entity comparison. The exact similarity measure used by
the system [11]
was derived from the one proposed in [10].
[1] Rose
Dieng and Stefan Hug. Comparison of "personal
ontologies" represented through conceptual graphs. In
Proc. 13th ECAI, Brighton (UK), pages 341–345, 1998.
[2]
An-Hai Doan, Jayant Madhavan, Pedro Domingos, and Alon
Halevy. Ontology matching: A machine learning approach.
In Steffen Staab and Rudi Studer, editors, Handbook
on Ontologies in Information Systems, pages 397–416.
Springer-Verlag, Heildelberg (DE), 2003.
[3]
Fausto Giunchiglia and Pavel Shvaiko. Semantic matching.
In Proc. IJCAI 2003 Workshop on ontologies and
distributed systems, pages 139– 146, 2003.
[4]
Jayant Madhavan, Philip Bernstein, and Erhard Rahm.
Generic schema matching using Cupid. In Proc. 27th
VLDB, Roma (IT), pages 48–58, 2001.
http://research.microsoft.com/
philbe/CupidVLDB0
[5]
Sergey Melnik, Hector Garcia-Molina, and Erhard Rahm.
Similarity flooding: a versatile graph matching
algorithm. In Proc. 18th International Conference on
Data Engineering (ICDE), San Jose (CA US), 2002.
[6]
Natalya Noy and Mark Musen. Anchor-PROMPT: Using
non-local context for semantic matching. In Proc.
IJCAI 2001 Workshop on ontology and information sharing,
Seattle (WA US), pages 63–70, 2001.
http://sunsite.informatik.rwth-aachen.de/Publications/CEURWS/Vol-47/
[7]
Erhard Rahm and Philip Bernstein. A survey of approaches
to automatic schema matching. VLDB Journal,
10(4):334–350, 2001.
[8]
Steffen Staab and Alexander Mädche. Measuring similarity
between ontologies. Lecture Notes in Artificial
Intelligence, 2473:251–263, 2002.
[9] Gerd
Stumme and Alexander Mädche. FCA-merge: bottom-up
merging of ontologies. In Proc. 17th IJCAI,
Seattle (WA US), pages 225–230, 2001.
[10] Petko Valtchev.
Construction automatique de taxonomies pour l’aide à la
représentation de connaissances par objets.
Thèse d’informatique,
Université Grenoble 1, 1999.
[11]
Jérôme Euzenat and Petko Valtchev. An integrative
proximity measure for ontology alignment. In Proc.
ISWC-2003 workshop on semantic information integration,
pages 33–38, Sanibel Island (FL US), 2003.
[12]
Jérôme Euzenat and Petko Valtchev. Similarity-based
ontology alignment in OWL-lite. In Proc. 15th ECAI,
pages 333–337, Valencia (ES), 2004. |