![](bg4.png)
Table 1: The SPARQL query using a semiotic-oriented up-
per ontology.
SELECT ?Expression WHERE { :Sun_Concept
dul:isExpressedBy ?Expression ?Language
dul:IsEncodedIn :it}
The same runs to retrieve lexical forms. Using a
simple SPARQL query we get several lexical forms
for the concepts Sun as depicted in Figure 4
Another interesting feature is the capability of
gathering all topics of a concept in synoptic view. By
using the class Topic, it is possible to put together all
categories to which the concept belongs.
Multilingual dictionaries often are limited to pro-
vide just the translations of terms without giving the
gloss. Glosses help to define the concept supporting
the sense understanding. WordNet (Miller, 1990) is a
good example of the use of glosses to define the sense
of a term. The class Description aims at providing
this additional information exploiting the first para-
graph of the Wikipedia article as a good candidate to
describe the concept.
6 CONCLUSIONS
In this paper we presented a novel technique to cre-
ate multilingual resources from DBpedia within a
semiotic-oriented upper ontology framework. We
showed limitations and potentialities of Dbpedia to be
used as a terminological repository. In order to fully
exploit this resource, we created a powerful ontologi-
cal structure based on well-founded semiotic theories.
In the future works, we plan to add new features
as the management of linguistic forms as discussed in
Section 1 and we plan to use it as support for multilin-
gual machine translation. We aim at creating a mul-
tilingual system able to translate from many-to-many
language using an ontological support.
ACKNOWLEDGEMENTS
This research has been funded by the Swiss National
Science Foundation (SNSF) for Project no. 127651
of the Individual Support Fellowship program. More-
over, I would like to thank Aldo Gangemi from the
Laboratory for Applied Ontology to share with me
some ideas concerning the theoretical foundations un-
derlying this paper.
REFERENCES
Auer, S., Bizer, C., Kobilarov, G., and Lehmann, J. (2007).
Dbpedia: A nucleus for a web of open data. In
proceedings of 6th Int’l Semantic Web Conference
(ISWC2007), pages 722–735.
Bentivogli, L., Pianta, E., and Girardi, C. (2002). Multi-
wordnet: developing an aligned multilingual database.
In First International Conference on Global WordNet,
Mysore, India.
Bizer, C. and Heath, T. (2007). Interlinking open data on the
web. In Proceedings Poster Track, Extended Semantic
Web Conference.
Fung, P. (1998). A statistical view on bilingual lexicon
extraction: From parallel corpora to non-parallel cor-
pora. In AMTA, pages 1–17.
Gangemi, A., Guarino, N., Masolo, C., and Oltramari, A.
(2002). Sweetening ontologies with dolce. In Pro-
ceedings of European Workshop on Knowledge Ac-
quisition, Modeling and Management (EKAW), pages
166–181.
Jain, P., Hitzler, P., Yehy, P. Z., Vermay, K., and Shet, A. P.
(2010). Linked data is merely more data. In Linked
Data Meets Artificial Intelligence, pages 82–86.
Kazama, J. and Torisawa, K. (2007). Exploiting wikipedia
as external knowledge for named entity recognition.
In Joint Conference on Empirical Methods in Natu-
ral Language Processing and Computational Natural
Language Learning, pages 698–707.
Miller, G. A. (1990). Nouns in wordnet: a lexical inheri-
tance system,. International Journal of Lexicography,
3(4):245–264.
Morin, E., Daille, B., Takeuchi, K., and Kageura, K. (2007).
Bilingual terminology mining - using brain, not brawn
comparable corpora. In ACL.
Peirce, C. S. (1958). Collected Papers of Charles Sanders
Peirce. MIT Press, Cambridge, Mass.
Picca, D., Gliozzo, A. M., and Gangemi, A. (2008). Lmm:
an owl-dl metamodel to represent heterogeneous lexi-
cal knowledge. In LREC.
Utsuro, T., Ikeda, H., Yamane, M., Matsumoto, Y., and Na-
gao, M. (1994). Bilingual text, matching using bilin-
gual dictionary and statistics. In Proceedings of the
15th conference on Computational linguistics, pages
1076–1082, Morristown, NJ, USA. Association for
Computational Linguistics.
Vossen, P. (2002). Eurowordnet: general document. Tech-
nical report.
W3C, C. (2009). Linkingopendata. http://bit.ly/dW03.
Yu, K. and Tsujii, J. (2009). Extracting bilingual dictio-
nary from comparable corpora with dependency het-
erogeneity. In NAACL ’09: Proceedings of Human
Language Technologies: The 2009 Annual Confer-
ence of the North American Chapter of the Associa-
tion for Computational Linguistics, Companion Vol-
ume: Short Papers, pages 121–124, Morristown, NJ,
USA. Association for Computational Linguistics.
BUILDING MULTILINGUAL LEXICAL RESOURCES ON SEMIOTIC PRINCIPLES
415