Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task
Shailaja Keyur Sampat, Pratyay Banerjee, Yezhou Yang, Chitta R. Baral · 2022
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 visionlanguage 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 encoderdecoder 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 1 .