7th International Conference on Natural Language Processing, Hyderabad
Cliques, Categories and Analogies: Building O Ontologies Bottom-Up: Keynote lecture 2 at ICON 2009, at IIIT Hyderabad, by Tony Veale, University College Dublin, Dublin.
Abstract
Similarity and comparability are complementary notions that are easy to
confuse and difficult to tease apart. Semantic similarity makes comparison
meaningful, while comparison is often the pragmatic means through which
similarity is perceived and constructed. To date, WordNet has found wide
application as a basis for modeling and measuring semantic similarity,
but is lacking as a basis for well-formed comparability judgments. In
this talk the speaker will describe a corpus-based approach to learning a model
of sensible comparability, and show how this pragmatic model can be integrated
with a WordNet-based notion of semantic similarity. This model
of comparability, called Mondrian, provides a convenient and efficient means
of supporting simple relational analogies between WordNet terms, and how
analogies of this kind can be used for the automatic acquisition of enriching
relational knowledge in WordNet.
Comparability and analogy can also play a role in aligning the sub-structures
of an ontology, either across different ontologies (in ontology mapping) or
within the same ontology (in analogical mapping). Analogies within an
ontology indicate the presence of higher-order similarities between instances
or categories that should be reflected in the fine-grained structure of the ontology
itself. The speaker will show how analogies between categories in the same ontology can
be detected via linguistic analysis of large text corpora, and further show how
these analogies can be clustered via clique-analysis to create meaningful new
category structures.
23rd nov 2009
The technical schedule has been released. ![]()
23rd nov 2009
Click here for details of the panel discussion. ![]()
ICON-2009 Secretariat
Language Technologies Research Centre
International Institute of Information Technology
Gachibowli
Hyderabad - 500032, India
Tel: +91-40.23001412
Fax: +91-40.66531413
icon2009@iiit.ac.in