James M. Rehg


2022

pdf bib
Transformer-based Localization from Embodied Dialog with Large-scale Pre-training
Meera Hahn | James M. Rehg
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

We address the challenging task of Localization via Embodied Dialog (LED). Given a dialog from two agents, an Observer navigating through an unknown environment and a Locator who is attempting to identify the Observer’s location, the goal is to predict the Observer’s final location in a map. We develop a novel LED-Bert architecture and present an effective pretraining strategy. We show that a graph-based scene representation is more effective than the top-down 2D maps used in prior works. Our approach outperforms previous baselines.
Search
Co-authors
Venues