- This event has passed.
Lecture Series: Mattia Di Gangi
October 15, 2019 @ 4:00 pm – 5:30 pm
Mattia is a third-year Ph.D. student at the University of Trento, Italy. In Trento, he is pursuing his research in the group of Machine Translation (MT) at Fondazione Bruno Kessler (FBK), where he could study many aspects before landing to his current research topic, direct speech-to-text translation. His research experience also includes an internship in 2016 at the CNR (National Council of Research) of Palermo, Italy, and one in 2019 at Amazon AI, in East Palo Alto, California. He received his M.Sc. in Computer Science in the context of a double degree program by the University of Palermo, Italy and the University Paris-Est Marne-la-Vallée, France.
Neural Machine Translation for Text and Speech
Neural machine translation (NMT) reached such impressive results in the last few years that some industrial players, imprudently, claimed to have reached human parity. In this talk, I will first introduce NMT and the sequence-to-sequence models that enable it. Then, we will move towards modern approaches to back-translations and multilingual NMT, which enable the training of stronger systems by adding more data. Finally, I will introduce direct speech-to-text translation, where a single system is used to translate speech into text in a target language without intermediate transcription. This is an exciting research area that is experiencing fast growth and attracting more and more groups from academia and industry, and some of its fundamental problems are still unsolved.