Multimedia Generative Script Learning for Task Planning

Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji


Abstract
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities. An important aspect of this process is the ability to capture historical states visually, which provides detailed information that is not covered by text and will guide subsequent steps. Therefore, we propose a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 5,652 tasks and 79,089 multimedia steps. This task is challenging in three aspects: the multimedia challenge of capturing the visual states in images, the induction challenge of performing unseen tasks, and the diversity challenge of covering different information in individual steps. We propose to encode visual state changes through a selective multimedia encoder to address the multimedia challenge, transfer knowledge from previously observed tasks using a retrieval-augmented decoder to overcome the induction challenge, and further present distinct information at each step by optimizing a diversity-oriented contrastive learning objective. We define metrics to evaluate both generation and inductive quality. Experiment results demonstrate that our approach significantly outperforms strong baselines.
Anthology ID:
2023.findings-acl.63
Original:
2023.findings-acl.63v1
Version 2:
2023.findings-acl.63v2
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
986–1008
Language:
URL:
https://aclanthology.org/2023.findings-acl.63
DOI:
10.18653/v1/2023.findings-acl.63
Bibkey:
Cite (ACL):
Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, and Heng Ji. 2023. Multimedia Generative Script Learning for Task Planning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 986–1008, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Multimedia Generative Script Learning for Task Planning (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.63.pdf
Video:
 https://aclanthology.org/2023.findings-acl.63.mp4