Challenges for the Multilingual Semantic Web
Walther von Hahn, Cristina Vertan · 2005
In this paper we give an overview of Semantic Web technologies and the impact of these ones for multilingual Web. We present a possible solution for improving the quality of on-line translation systems, using mechanisms and standards from Semantic Web. We focus on Example based machine translation and the automatization of the translation examples extraction by means of RDF-repositories. 1 Basic Principles of Semantic Web In WWW are used each year more than 5 Billion Documents from more than 800 million active users. However, up to now is WWW self-organised System without any predefined or standardised structure or administration. The huge the quantity of information in WWW becomes the more difficult its administration is. Especially the update and targeted retrieval of information are more and more difficult. Usually the information is retrieved following a key-word search. This lexical search creates several problems:- too strong specialisation (better information about „violin “ can be found maybe under „string instruments “ or 2instruments“), because of- too many different specialised meanings, here for e.g. „instruments “ are only „music instruments “ but no surgery instruments.- No possibility of searching also synonyms