AI and Education Initiative Human and Machine Learning Lunch Series with Naomi Caselli, PhD

Speaker: Naomi Caselli, PhD, Associate Professor, Deaf Education, Boston University

Talk Title: Sign Language Recognition, Generation, and Translation: An Interdisciplinary Perspective

Bio: Naomi Caselli is an Associate Professor at the Wheelock College of Education & Human Development at Boston University. She is also the director of the AI & Education Initiative at the Hariri Institute for Computing. She realizes that deaf children have limited access to language early in life: often these children’s role models do not know how to sign and cannot hear the sounds of spoken languages. Incomplete acquisition of their first language, otherwise called language deprivation, inspired Caselli’s research. She is interested in the effects of language deprivation during early childhood of deaf children and how people learn American Sign Language (ASL). She has developed the ASL-CDI, an ASL adaptation of the MacArthur Bates Communicative Development Inventory, that assesses ASL vocabulary in children younger than five. Currently, she leads three National Science Foundation (NSF) and National Institutes of Health (NIH) grant funded projects. The first works on developing ASL-LEX, a database documenting the structure of the American Sign Language lexicon. The second focuses on understanding how visual modality shapes the ASL lexicon. The third project examines factors that shape vocabulary acquisition among deaf children who are and are not at risk for language deprivation.