Multitask Multimodal Prompted Training for Interactive Embodied Task Completion

Georgios Pantazopoulos, Malvina Nikandrou, Amit Parekh, Bhathiya Hemanthage, Arash Eshghi, Ioannis Konstas, Verena Rieser, Oliver Lemon, Alessandro Suglia


Abstract
Interactive and embodied tasks pose at least two fundamental challenges to existing Vision & Language (VL) models, including 1) grounding language in trajectories of actions and observations, and 2) referential disambiguation. To tackle these challenges, we propose an Embodied MultiModal Agent (EMMA): a unified encoder-decoder model that reasons over images and trajectories, and casts action prediction as multimodal text generation. By unifying all tasks as text generation, EMMA learns a language of actions which facilitates transfer across tasks. Different to previous modular approaches with independently trained components, we use a single multitask model where each task contributes to goal completion. EMMA performs on par with similar models on several VL benchmarks and sets a new state-of-the-art performance (36.81% success rate) on the Dialog-guided Task Completion (DTC), a benchmark to evaluate dialog-guided agents in the Alexa Arena.
Anthology ID:
2023.emnlp-main.50
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
768–789
Language:
URL:
https://aclanthology.org/2023.emnlp-main.50
DOI:
10.18653/v1/2023.emnlp-main.50
Bibkey:
Cite (ACL):
Georgios Pantazopoulos, Malvina Nikandrou, Amit Parekh, Bhathiya Hemanthage, Arash Eshghi, Ioannis Konstas, Verena Rieser, Oliver Lemon, and Alessandro Suglia. 2023. Multitask Multimodal Prompted Training for Interactive Embodied Task Completion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 768–789, Singapore. Association for Computational Linguistics.
Cite (Informal):
Multitask Multimodal Prompted Training for Interactive Embodied Task Completion (Pantazopoulos et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.50.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.50.mp4