Abstract Deep Neural Networks (DNNs) are powerful models that have achieved excellent
performance on difficult learning tasks. Although DNNs work well whenever large labeled …

Towards Effective Use of Training Data in Statistical Machine Translation Page 1 Proceedings
of the 7th Workshop on Statistical Machine Translation, pages 317–321, Montréal, Canada …

This paper describes the three systems developed by the LIUM for the IWSLT 2011
evaluation campaign. We participated in three of the proposed tasks, namely the Automatic …

In this paper, we present an approach for topic-level search and hyperlinking of video
snippets, which relies on content-based recommendation and multimodal re-ranking …

The Idiap system for search and hyperlinking uses topic-based segmentation, content-based
recommendation algorithms, and multimodal re-ranking. For both sub-tasks, our system …

The main metric used for SMT systems evaluation an optimisation is BLEU score but this
metric is questioned about its relevance to human evaluation. Some other metrics already …

This paper describes our approach and results in the hyperlinking sub-task at MediaEval
2013. A two step method is implemented where the fi rst step consists in establishing a …

This paper deals with Information Retrieval from audio-visual recordings. Such recordings
are often quite long and users may want to find the exact starting points of relevant passages …

The paper describes the Charles University setup used in the Search and Hyperlinking task
of the MediaEval 2012 Multimedia Benchmark. We applied the Terrier retrieval system to the …