Invited Speaker: David Bamman - TUFTS University, USA
Digital libraries become increasingly the main resource for knowledge sharing. Web technology enable that documents physically situated overall in the world, are collected together and can be browsed from anywhere in the world. Semantic Web methods allow additionally knowledge-based reasoning across documents.
A major challenge in this scenario is the multilingual dimension. Cross-lingual information retrieval technologies have the power to manage multilingual content and present to the user. However understanding this content still remains a problem, as long as it is written in a language less or unknown to the user.
Machine Translation and Machine Aided Translation play a major role in making digital libraries available to a broad spectrum of users. Very often users are only interested if the document is really relevant fort them, or if it contains new information. Therefore even partial translation (e.g. of lexical items or syntactic chunks) can be helpful.
Digital libraries are on the other hand not only beneficiaries of MT-systems but can provide useful material for improvement of translation technologies. The massive amount of corpora can be used as training sets for language models, sources for improvement of lexicons etc.
The aim of this workshop is to investigate to which extent digital libraries and translation technologies can benefit one of the other and bring together researchers in both domains.
02 May 2009