@inproceedings{44e9f5c3c14c4b2aaa22901208c9183e,
title = "Multilingual text classification using ontologies",
abstract = "In this paper, we investigate strategies for automatically classifying documents in different languages thematically, geographically or according to other criteria. A novel linguistically motivated text representation scheme is presented that can be used with machine learning algorithms in order to learn classifications from pre-classified examples and then automatically classify documents that might be provided in entirely different languages. Our approach makes use of ontologies and lexical resources but goes beyond a simple mapping from terms to concepts by fully exploiting the external knowledge manifested in such resources and mapping to entire regions of concepts. For this, a graph traversal algorithm is used to explore related concepts that might be relevant. Extensive testing has shown that our methods lead to significant improvements compared to existing approaches.",
author = "{De Melo}, Gerard and Stefan Siersdorfer",
year = "2007",
doi = "10.1007/978-3-540-71496-5_49",
language = "English (US)",
isbn = "3540714944",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "541--548",
booktitle = "Advances in Information Retrieval - 29th European Conference on IR Research, ECIR 2007, Proceedings",
address = "Germany",
note = "29th European Conference on IR Research, ECIR 2007 ; Conference date: 02-04-2007 Through 05-04-2007",
}