Visuo-Linguistic Question Answering (VLQA) Challenge

Shailaja Keyur Sampat, Yezhou Yang, Chitta Baral

Abstract
Understanding images and text together is an important aspect of cognition and building advanced Artificial Intelligence (AI) systems. As a community, we have achieved good benchmarks over language and vision domains separately, however joint reasoning is still a challenge for state-of-the-art computer vision and natural language processing (NLP) systems. We propose a novel task to derive joint inference about a given image-text modality and compile the Visuo-Linguistic Question Answering (VLQA) challenge corpus in a question answering setting. Each dataset item consists of an image and a reading passage, where questions are designed to combine both visual and textual information i.e., ignoring either modality would make the question unanswerable. We first explore the best existing vision-language architectures to solve VLQA subsets and show that they are unable to reason well. We then develop a modular method with slightly better baseline performance, but it is still far behind human performance. We believe that VLQA will be a good benchmark for reasoning over a visuo-linguistic context. The dataset, code and leaderboard is available at https://shailaja183.github.io/vlqa/.
Anthology ID:
2020.findings-emnlp.413
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4606–4616
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.413
DOI:
10.18653/v1/2020.findings-emnlp.413
Bibkey:
Cite (ACL):
Shailaja Keyur Sampat, Yezhou Yang, and Chitta Baral. 2020. Visuo-Linguistic Question Answering (VLQA) Challenge. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4606–4616, Online. Association for Computational Linguistics.
Cite (Informal):
Visuo-Linguistic Question Answering (VLQA) Challenge (Sampat et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.findings-emnlp.413.pdf
Optional supplementary material:
 2020.findings-emnlp.413.OptionalSupplementaryMaterial.pdf
Data
AI2D, ARC, TQA, VCR, Visual Question Answering
PDF Search Optional supplementary material