This website uses cookies

The website of the Fundació Politècnica de Catalunya uses its own and third-party cookies to improve the browsing experience and for statistical purposes. For more information about cookies you can consult the cookie policy.

Manage cookies
Allow all cookies
Campus
MY_TECH_SPACE


Go
Campus in maintenance
User and / or password incorrect
You have no active environment
Your access has been restricted. Consultation with the department of administration
Due to technical problems, the virtual campus is inaccessible. We are working to solve it. Sorry for the inconvenience.
You are not authorized to make this call. You can consult webmaster.fpc@fpc.upc.edu
You have exceeded the maximum number of attempts. Your user is temporarily blocked. Check back in a little while.
You must enter your campus username, not an email
You have to perform the verification to verify that you are not a robot.
Start   >  Events  >  Open Class "A Deep Vision of Lifelong Learning Multilingu...
Date: 22-10-2020
Timetable: 6:30 pm to 7:30 pm
Location: Online
Contact: 931146805

An Open Class is to be held at 06:30 PM on thursday 22-10-2020 on Postgraduate in Artificial Intelligence with Deep Learning (Online).

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.

The speaker

Marta Ruiz 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).



The session will take place on-line using Google Meet (Hangouts Meet).

Requirements for the on-line connection

*To be able to follow the informational session on-line we recommend that you use either speakers or headphones and have at least a 3MB internet connection.

As well, you can follow the informational session using your smartphone by downloading the corresponding Google Meet (Hangouts Meet) application for your Android or iPhone, iPad or iPod Touch.

This event is open and free. To attend, please confirm using the "I Will attend". Limited places.