Grounding Language by Seeing, Hearing, and Interacting
As humans, our understanding of language is grounded in a rich mental model about “how the world works” – that we learn through perception and interaction. We use this understanding to reason beyond what is literally said, imagining how situations might unfold in the world. Machines today struggle at making such connections, which limits how they can be safely used.
In my talk, I will discuss three lines of work to bridge this gap between machines and humans. I will first discuss how we might measure grounded understanding. I will introduce a suite of approaches for constructing benchmarks, using machines in the loop to filter out spurious biases. Next, I will introduce PIGLeT: a model that learns physical commonsense understanding by interacting with the world through simulation, using this knowledge to ground language. PIGLeT learns linguistic form and meaning – together – and outperforms text-to-text only models that are orders of magnitude larger. Finally, I will introduce MERLOT, which learns about situations in the world by watching millions of YouTube videos with transcribed speech. The model learns to jointly represent video, audio, and language, together and over time – learning multimodal and neural script knowledge representations. Together, these directions suggest a path forward for building machines that learn language rooted in the world.
Host: Chenhao Tan
Rowan Zellers is a final year PhD candidate at the University of Washington in Computer Science & Engineering, advised by Yejin Choi and Ali Farhadi. His research focuses on enabling machines to understand language, vision, sound, and the world beyond these modalities. He has been recognized through NSF and ARCS Graduate Fellowships, and a NeurIPS 2021 outstanding paper award. His work has appeared in several media outlets, including Wired, the Washington Post, and the New York Times. In the past, he graduated from Harvey Mudd College with a B.S. in Computer Science & Mathematics, and has interned at the Allen Institute for AI.