Center for Language and Speech Processing

Paco Guzman (Meta AI) “Building a Universal Translation System to Break Down Language Barriers”

Calendar
When:
April 17, 2023 @ 12:00 pm – 1:15 pm
2023-04-17T12:00:00-04:00
2023-04-17T13:15:00-04:00
Where:
Hackerman Hall B17
3400 N. Charles Street
Baltimore
MD 21218
Cost:
Free
Seminars
2023 April Guzman

Abstract

Machine Translation has the ultimate goal of eliminating language barriers. However, the area has focused mainly on a few languages, leaving many low-resource languages without support. In this talk, I will discuss the challenges of bringing translation support for 200 written languages and beyond.
First, I talk about the No Language Left Behind Project, where we took on this challenge by first contextualizing the need for low-resource language translation support through exploratory interviews with native speakers. Then, we created datasets and models aimed at narrowing the performance gap between low and high-resource languages. We proposed multiple architectural and training improvements to counteract over-fitting while training on thousands of language-pairs/tasks. We evaluated the performance of over 40,000 different translation directions.
Afterwards, I’ll discuss the challenges of pushing translation performance beyond text for languages that don’t have written standards like Hokkien.

Our models achieve state-of-the-art performance and lay important groundwork towards realizing a universal translation system. At the same time, we keep making open-source contributions for everyone to keep advancing the research for the languages they care about.

Bio

Paco is Research Scientist Manager supporting translation teams in Meta AI (FAIR). He works in the field of machine translation with a focus on low-resource translation (e.g. NLLB, FLORES) and the aim to break language barriers. He joined Meta in 2016. His research has been published in top-tier NLP venues like ACL, EMNLP. He was the co-chair of the Research director at AMTA (2020-2022). He has ave organized several research competitions focused on low-resource translation and data filtering. Paco obtained his PhD from the ITESM in Mexico, was a visiting scholar at the LTI-CMU from 2008-2009, and participated in DARPA’s GALE evaluation program. Paco was a post-doc and scientist at Qatar Computing Research Institute in Qatar in 2012-2016

Center for Language and Speech Processing