What is Multimodality?
Abstract
The last years have shown rapid developments in the field of multimodal machine learning, combining e.g., vision, text or speech. In this position paper we explain how the field uses outdated definitions of multimodality that prove unfit for the machine learning era. We propose a new task-relative definition of (multi)modality in the context of multimodal machine learning that focuses on representations and information that are relevant for a given machine learning task. With our new definition of multimodality we aim to provide a missing foundation for multimodal research, an important component of language grounding and a crucial milestone towards NLU.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2021
- DOI:
- 10.48550/arXiv.2103.06304
- arXiv:
- arXiv:2103.06304
- Bibcode:
- 2021arXiv210306304P
- Keywords:
-
- Computer Science - Artificial Intelligence;
- Computer Science - Computation and Language;
- Computer Science - Computer Vision and Pattern Recognition;
- 68Txx;
- I.2.0;
- I.2.7;
- I.2.10
- E-Print:
- Paper accepted for publication at MMSR 2021