What is Multimodality?
This is a foundational position paper that addresses a conceptual gap in multimodal machine learning, which is crucial for language grounding and natural language understanding.
The paper identifies outdated definitions of multimodality in machine learning and proposes a new task-relative definition based on representations and information relevant to specific tasks, aiming to provide a foundational framework for multimodal research.
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 In this position paper we explain how the field uses outdated definitions of multimodality that prove unfit for the machine learning era.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.