Visual Semantic Parsing: From Images to Abstract Meaning Representation

Mohamed Ashraf Abdelsalam, Zhan Shi, Federico Fancellu, Kalliopi Basioti, Dhaivat Bhatt, Vladimir Pavlovic, Afsaneh Fazly


Abstract
The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e.g., image) into a structured representation, where entities (people and objects) are nodes connected by edges specifying their relations. Building these representations, however, requires expensive manual annotation in the form of images paired with their scene graphs or frames. These formalisms remain limited in the nature of entities and relations they can capture. In this paper, we propose to leverage a widely-used meaning representation in the field of natural language processing, the Abstract Meaning Representation (AMR), to address these shortcomings. Compared to scene graphs, which largely emphasize spatial relationships, our visual AMR graphs are more linguistically informed, with a focus on higher-level semantic concepts extrapolated from visual input. Moreover, they allow us to generate meta-AMR graphs to unify information contained in multiple image descriptions under one representation. Through extensive experimentation and analysis, we demonstrate that we can re-purpose an existing text-to-AMR parser to parse images into AMRs. Our findings point to important future research directions for improved scene understanding.
Anthology ID:
2022.conll-1.19
Volume:
Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Antske Fokkens, Vivek Srikumar
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
282–300
Language:
URL:
https://aclanthology.org/2022.conll-1.19
DOI:
10.18653/v1/2022.conll-1.19
Bibkey:
Cite (ACL):
Mohamed Ashraf Abdelsalam, Zhan Shi, Federico Fancellu, Kalliopi Basioti, Dhaivat Bhatt, Vladimir Pavlovic, and Afsaneh Fazly. 2022. Visual Semantic Parsing: From Images to Abstract Meaning Representation. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 282–300, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Visual Semantic Parsing: From Images to Abstract Meaning Representation (Abdelsalam et al., CoNLL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2022.conll-1.19.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2022.conll-1.19.mp4