Machine Translation (MT) tools are more accessible than ever, but a key challenge remains: how can we help users rely on them appropriately, especially when they don't understand one of the languages involved? This talk will describe how my group has addressed this problem in recent years.
I'll begin by sharing the results of user studies designed to understand how people build trust in and reliance on MT. These findings led us to reframe MT evaluation to provide actionable feedback that helps people assess the impact of translation errors. To achieve this, we introduce techniques based on large language models to ask and answer questions about a translated text, and to detect errors in speech translations with minimal supervision.
Throughout the talk, I will highlight open questions and research directions for designing language technology that genuinely supports people in communicating across language barriers.
Marine Carpuat is an Associate Professor of Computer Science at the University of Maryland. Her research focuses on multilingual natural language processing and machine translation, with the goal of designing technology that helps people communicate regardless of the language they speak. Before her faculty position at Maryland, she was a Research Scientist at the National Research Council Canada. Dr. Carpuat earned a PhD in Computer Science and an MPhil in Electrical Engineering from the Hong Kong University of Science & Technology, as well as a Diplôme d'Ingénieur from the French Grande École Supélec. Her work has been recognized with an NSF CAREER Award, paper awards at the *SEM, TALN, and EMNLP conferences, and an Outstanding Teaching Award. She also served as a Program Co-Chair for NAACL 2022.