Neuronové reprezentace v multimodálním a mnohojazyčném modelování

grant

deep learning;machine learning;neural networks;continuous representations;natural language processing;speech and text processing;machine translation;multi-modality;multi-linguality

The NEUREM3 project encompasses basic research in speech processing (SP) and natural language processing (NLP) with accent on multi-linguality and multi-modality (speech and text processing with the support of visual information). Current deep machine learning methods are based on continuous vector representations that are created by the neural networks (NN) themselves during the training. Although empirically, the results of such NNs are often excellent, our knowledge and understanding of such representations is insufficient. NEUREM3 has an ambition to fill this gap and to study neural representations for speech and text units of different scopes (from phonemes and letters to whole spoken and written documents) and representations acquired both for isolated tasks and multi-task setups. NEUREM3 will also improve NN architectures and training techniques, so that they can be trained on incomplete or incoherent data.

Burget Lukáš, doc. Ing., Ph.D. (UPGM FIT VUT) , research leader
Karafiát Martin, Ing., Ph.D. (UPGM FIT VUT) , team leader
Veselý Karel, Ing., Ph.D. (UPGM FIT VUT) , team leader
Baskar Murali K. (UPGM FIT VUT)
Beneš Karel, Ing. (UPGM FIT VUT)
Kohlová Renata, Ing. (UPGM FIT VUT)
Otáhalová Sylva (UPGM FIT VUT)
Silnova Anna, MSc. (UPGM FIT VUT)
Vydana Hari K. (UPGM FIT VUT)