Elpub : Digital Library : Works

Paper 117_elpub2006:
Searching and Summarizing in a Multilingual Environment

id 117_elpub2006
authors Toman, Michal; Steinberger, Josef; Jezek, Karel
year 2006
title Searching and Summarizing in a Multilingual Environment
source ELPUB2006. Digital Spectrum: Integrating Technology and Culture - Proceedings of the 10th International Conference on Electronic Publishing held in Bansko, Bulgaria 14-16 June 2006 / Edited by: Bob Martens, Milena Dobreva. ISBN 978-954-16-0040-5, 2006, pp. 257-266
summary Multilingual aspects are gaining more attention in recent years. This direction is further broadened by a global integration of the European states and vanishing cultural and social boundaries. The spread of foreign languages is even bigger with the information boom caused by an emergence of easy internet access. Multilingual text processing becomes an important area, which brings a lot of new and interesting problems. Their possible solutions are proposed in this paper. The first part of this contribution is devoted to methods for multilingual searching, the second part deals with summarization of retrieved texts. We tested some novel processing techniques: a language-independent storage format, semantic-based indexing, query expansion or text summarization leading to faster and easier retrieval and understanding of documents. We implemented a prototype system named MUSE (Multilingual Searching and Extraction) and evaluated its qualities against the state-of-the-art searching engine - Google. The results seem to be promising; MUSE shows high correlation with market-leading products. Although our experiments were performed on Czech and English articles, the main principle remains the same for other languages.
keywords multilingual text processing; searching; summarization; EuroWordNet
series ELPUB:2006
type normal paper
email mtoman@kiv.zcu.cz
more http://www.elpub.net
content file.pdf (278,956 bytes)
discussion No discussions. Post discussion ...
urn:nbn urn:nbn:se:elpub-117_elpub2006
last changed 2006/05/20 11:20
HOMELOGIN (you are user _anon_951929 from group guest) Powered by SciX Open Publishing Services 1.002