Title: Toward Human-Centered Machine Translation
Abstract: In this talk, I will describe current research directions in my group that revisit the steps of the Machine Translation (MT) research and development lifecycle to design systems that help people communicate across language barriers. These range from methods to better characterize the degree of parallelism in the data that powers MT systems, new models such as a non-autoregressive Transformer that enable flexible conditional language generation, and new framings of machine translation tasks and evaluation to center human factors.
Bio: Marine Carpuat is an Associate Professor in Computer Science at the University of Maryland. Her research focuses on multilingual natural language processing and machine translation. Before joining the faculty at Maryland, she was a Research Scientist at the National Research Council Canada. She received a PhD in Computer Science and a MPhil in Electrical Engineering from the Hong Kong University of Science & Technology, and a Diplome d'Ingenieur from the French Grande Ecole Supelec. She is the recipient of an NSF CAREER award, research awards from Google and Amazon, best paper awards at *SEM and TALN, and an Outstanding Teaching Award.
To obtain the Zoom link for this event, please see the event announcements from MLFL on the college email lists or contact wenlongzhao [at] cs.umass.edu (subject: MLFL%20Zoom%20Link) (Wenlong Zhao).