Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models

Eva Portelance

HEC Montreal

The NLP Reading Group is excited to host Eva Portelance, an assistant professor at HEC Montreal, who will be speaking in person in Auditorium 2 at 11:30 AM on Friday October 18th about joint learning in language acquisition.

Talk Description

Semantic and syntactic bootstrapping posit that children use their prior knowledge of one linguistic domain, say syntactic relations, to help later acquire another, such as the meanings of new words. Empirical results supporting both theories may tempt us to believe that these are different learning strategies, where one may precede the other. Here, we argue that they are instead both contingent on a more general learning strategy for language acquisition: joint learning. Using a series of neural visually-grounded grammar induction models, we demonstrate that both syntactic and semantic bootstrapping effects are strongest when syntax and semantics are learnt simultaneously. Joint learning results in better grammar induction, realistic lexical category learning, and better interpretations of novel sentence and verb meanings. Joint learning makes language acquisition easier for learners by mutually constraining the hypotheses spaces for both syntax and semantics. Studying the dynamics of joint inference over many input sources and modalities represents an important new direction for language modeling and learning research in both cognitive sciences and AI, as it may help us explain how language can be acquired in more constrained learning settings.

Speaker Bio

Eva Portelance is an Assistant Professor of machine learning in the Department of decision sciences at HEC Montréal and a member of Mila — Québec Artificial Intelligence Institute. Her research intersects AI and cognitive science; She is interested in understanding how both humans and machines learn to understand language and reason about complex problems. Previously, she was a postdoc at Mila and McGill University with Timothy J. O’Donnell and Siva Reddy. Her Ph.D. was in computational/cognitive linguistics from Stanford University, where she worked with Dan Jurafsky and Mike C. Frank.

Logistics

Date: October 18th
Time: 11:30AM
Location: Auditorium 2 or via Zoom (See email)