Transformer-based Localization from Embodied Dialog with Large-scale Pre-training

Meera Hahn, James M. Rehg


Abstract
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.
Anthology ID:
2022.aacl-short.36
Volume:
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)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
295–301
Language:
URL:
https://aclanthology.org/2022.aacl-short.36
DOI:
Bibkey:
Cite (ACL):
Meera Hahn and James M. Rehg. 2022. Transformer-based Localization from Embodied Dialog with Large-scale Pre-training. In 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), pages 295–301, Online only. Association for Computational Linguistics.
Cite (Informal):
Transformer-based Localization from Embodied Dialog with Large-scale Pre-training (Hahn & Rehg, AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.aacl-short.36.pdf