Contribution of NLP to the Content Indexing of Multimedia Documents

Thierry Declerck, J. Kuper, H. Saggion, A. Samiotou, P. Wittenburg, J. Contreras

In: Seiten 610-618 Lecture Notes in Computer Science 3115 / 2004 Springer-Verlag Heidelberg 6/2004.


This paper describes the role natural language processing (NLP) can play for multimedia applications. As an example of such an application, we present an approach dealing with the conceptual indexing of soccer videos which the help of structured information automatically extracted by NLP tools from multiple sources of information relating to video content, consisting in a rich range of textual and transcribed sources covering soccer games. This work has been investigated and developed in the EU funded project MUMIS. As a second example of such an application, we describe briefly ongoing work in the context of the Esperonto project dealing with upgrading the actual web towards the Semantic Web (SW), including the automatic semantic indexing of web pages containing a combination of text and images.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence