BibTeX

@inProceedings{hagstrom-johansson-2022-small-318477,
	title        = {Can We Use Small Models to Investigate Multimodal Fusion Methods?},
	abstract     = {Many successful methods for fusing language with information from the visual modality have recently been proposed and the topic of multimodal training is ever evolving. However, it is still largely not known what makes different vision-and-language models successful. Investigations into this are made difficult by the large sizes of the models used, requiring large training datasets and causing long train and compute times. Therefore, we propose the idea of studying multimodal fusion methods in a smaller setting with small models and datasets. In this setting, we can experiment with different approaches for fusing multimodal information with language in a controlled fashion, while allowing for fast experimentation. We illustrate this idea with the math arithmetics sandbox. This is a setting in which we fuse language with information from the math modality and strive to replicate some fusion methods from the vision-and-language domain. We find that some results for fusion methods from the larger domain translate to the math arithmetics sandbox, indicating a promising future avenue for multimodal model prototyping.},
	booktitle    = {Proceedings of the 2022 CLASP Conference on (Dis)embodiment, Gothenburg, Sweden, pages 45-50.},
	author       = {Hagström, Lovisa and Johansson, Richard},
	year         = {2022},
	publisher    = {Association for Computational Linguistics},
}