CLIP 2005, the 1st Clustering techniques for document organisation and retrieval,
16-17 June 2005, University of Genova, Italy

Cross-language information processing is the task of processing information expressed in more than one language. Examples include categorizing collections of documents written in several languages, language identification, automatic understanding of texts containing sentences in more than one language, question answering where questions are asked in a different language than answers.

There are several reference activities regarding multiple European languages on one side, and English/Asian languages on the other side. However, the present workshop aims at presenting work made in the specific field of European-Indian cross-language information processing, as well as language-independent methods which can be applied to less-studied languages.

This year's workshop was focused on methods for organizing information and documents from multilingual sources. One obvious such source is the World-Wide Web.

The main subject area in document organization is probably clustering, and we will devote this edition to the discussion of clustering techniques in a multilingual environment. Methods specifically designed will be presented, with case studies from specific application fields.

For further information please visit this web site: