A Deep Vision of Lifelong Learning Multilingual Machine Translation

Multilingual Machine Translation is at the core of social communication. In everyday situations, we rely on free commercial services. These systems have improved their quality thanks to the use of deep learning techniques. More than this, architectures initially developed for solving machine translation are now used in many other applications such as gaming or recommendation systems. Despite the huge progress that machine translation is doing, why do we still see that translation quality is much better in English to Portuguese than between spoken Dutch and Catalan?

In this talk, we are going to give some deep insights into (spoken) multilingual language translation pursuing similar quality for all languages. Also, we are going to discuss how we can efficiently add new languages in a highly multilingual system. Finally, we are going to give details on the fairness challenge, why neutral words as “doctor” tend to infer the “male” gender when translated into a language that requires gender flexion for this word?

In going through these issues, this talk will give an overview of the challenges and research directions in the field of multilingual machine translation.

Short bio: 

Marta R. Costa-jussà is a Ramon y Cajal Researcher at the Universitat Politècnica de Catalunya (UPC, Barcelona). She received her PhD from the UPC in 2008. Her research experience is mainly in Machine Translation. She has worked at LIMSI-CNRS (Paris), Barcelona Media Innovation Center, Universidade de São Paulo, Institute for Infocomm Research (Singapore), Instituto Politécnico Nacional (Mexico) and the University of Edinburgh. Recently, she has received an ERC Starting Grant 2020 and two Google Faculty Research Awards (2018 and 2019).