English

Multimodal Conversational AI: A Survey of Datasets and Approaches

Machine Learning 2022-05-17 v1

Abstract

As humans, we experience the world with all our senses or modalities (sound, sight, touch, smell, and taste). We use these modalities, particularly sight and touch, to convey and interpret specific meanings. Multimodal expressions are central to conversations; a rich set of modalities amplify and often compensate for each other. A multimodal conversational AI system answers questions, fulfills tasks, and emulates human conversations by understanding and expressing itself via multiple modalities. This paper motivates, defines, and mathematically formulates the multimodal conversational research objective. We provide a taxonomy of research required to solve the objective: multimodal representation, fusion, alignment, translation, and co-learning. We survey state-of-the-art datasets and approaches for each research area and highlight their limiting assumptions. Finally, we identify multimodal co-learning as a promising direction for multimodal conversational AI research.

Keywords

Cite

@article{arxiv.2205.06907,
  title  = {Multimodal Conversational AI: A Survey of Datasets and Approaches},
  author = {Anirudh Sundar and Larry Heck},
  journal= {arXiv preprint arXiv:2205.06907},
  year   = {2022}
}

Comments

17 pages, 1 figure, to be published in the 4th Workshop on NLP for Conversational AI