BibTeX

@inProceedings{hagstrom-johansson-2022-what-316251,
	title        = {What do Models Learn From Training on More Than Text? Measuring Visual Commonsense Knowledge},
	abstract     = {There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from multimodal training. We hypothesize that training on a visual modality should improve on the visual commonsense knowledge in language models. Therefore, we introduce two evaluation tasks for measuring visual commonsense knowledge in language models (code publicly available at: github.com/lovhag/measure-visual-commonsense-knowledge) and use them to evaluate different multimodal models and unimodal baselines. Primarily, we find that the visual commonsense knowledge is not significantly different between the multimodal models and unimodal baseline models trained on visual text data.},
	booktitle    = {    Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop,  pp. 252–261, Dublin, Ireland},
	author       = {Hagström, Lovisa and Johansson, Richard},
	year         = {2022},
	publisher    = {Association for Computational Linguistics},
}