The lecturer and researcher Marta Ruiz Costa-Jussà has been selected in the Google Faculty Research Awards for the second year running for a project on a multilingual automatic translation system for voice and text.
Marta Ruiz Costa-Jussà, lecturer and researcher at the Universitat Politècnica de Catalunya · BarcelonaTech (UPC), has been selected in the Google Faculty Research Awards for the project ‘Interlingua-based Neural Machine Translation to reduce complexity and better exploit low resources in highly multilingual environments’. The project explores an automatic translation system that introduces automatic learning of a universal language (i.e. interlingua). That is, the aim is to automatically generate a kind of “Esperanto” that serves as a bridge to translate voice or text between two languages, whatever they are. Compared to current systems, this system will enable multilingual translation to be more easily extended from text to voice, and new languages to be incorporated in automatic translators more efficiently.
It is the second time that this project has won an award in the category ‘Machine Translation’. The Google Faculty Research Awards is one of the most prestigious international awards for computer science and engineering, that grants awards for research in the technology field in the areas of quantum computing, automatic learning, algorithms or natural language processing, among others. The grants provide the opportunity to work directly with Google researchers and engineers.
The project, which started last year, proposes a modification in the computational architecture of the automatic translator to learn universal language effortlessly.
Marta Ruiz Costa-Jussà is a researcher at the Intelligent Data Science and Artificial Intelligence (IDEAI) research centre and is also part of the Centre for Language and Speech Technologies and Applications (TALP) and the Speech Processing Group (VEU) at the UPC. She is a lecturer at the Barcelona School of Telecommunications Engineering (ETSETB) and the Barcelona School of Informatics (FIB) and joint academic director of the postgraduate programme Artificial Intelligence with Deep Learning of the UPC School. She has also worked in the Laboratoire de Recherche Pluridisciplinaire (LIMSI-CNRS) in Paris, and at the Centre d’Innovació Media de Barcelona, the University of São Paulo, Infocomm Research Institute of Singapore, the National Technological Institute of Mexico and the University of Edinburgh.