The activities of the Machine Translation group began some years ago with the use of finite-state models for speech-to-speech translation and for text-to-text translation in limited domains. This group has developed a number of translation models with the corresponding learning algorithms and a number of prototypes for speech translation and computer-assisted translation.
Currently, the Machine Translation group is devoted to the development of new interactive-predictive techniques for computer-assisted translation, techniques for domain adaptation and for continuous text representations.
- Statistical machine translation
- Neural machine translation
- Interactive machine translation
- Multimodal machine translation
- Audio and video description
- Speech translation