UNED at MediaEval 2010: exploiting text metadata for Automatic Video Tagging

In this paper we present the rst participation of the NLP&IR group at UNED in the Tagging Task (Professional Version): prediction of semantic theme. This categorization task was carried out by an information retrieval approach, together with language models and clustering using only metadata associated with the videos. The results show that language models are useful for enriching the representation of information associated with videos.