Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task

Shailaja Keyur Sampat, Pratyay Banerjee, Yezhou Yang, Chitta Baral


Abstract
‘Actions’ play a vital role in how humans interact with the world. Thus, autonomous agents that would assist us in everyday tasks also require the capability to perform ‘Reasoning about Actions & Change’ (RAC). This has been an important research direction in Artificial Intelligence (AI) in general, but the study of RAC with visual and linguistic inputs is relatively recent. The CLEVR_HYP (Sampat et. al., 2021) is one such testbed for hypothetical vision-language reasoning with actions as the key focus. In this work, we propose a novel learning strategy that can improve reasoning about the effects of actions. We implement an encoder-decoder architecture to learn the representation of actions as vectors. We combine the aforementioned encoder-decoder architecture with existing modality parsers and a scene graph question answering model to evaluate our proposed system on the CLEVR_HYP dataset. We conduct thorough experiments to demonstrate the effectiveness of our proposed approach and discuss its advantages over previous baselines in terms of performance, data efficiency, and generalization capability.
Anthology ID:
2022.findings-emnlp.436
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5914–5924
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.436
DOI:
10.18653/v1/2022.findings-emnlp.436
Bibkey:
Cite (ACL):
Shailaja Keyur Sampat, Pratyay Banerjee, Yezhou Yang, and Chitta Baral. 2022. Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5914–5924, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task (Sampat et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.436.pdf