Emergent Communication with Attention

Abstract

To develop computational agents that can better communicate with others using their own emergent language, we endow the agents with an ability to focus their attention on particular concepts in the environment. Humans often understand a thing or scene as a composite of concepts and those concepts are further mapped onto words. We implement this intuition as attention mechanisms in Speaker and Listener agents in a referential game and show attention leads to more compositional and interpretable emergent language. We also demonstrate how attention helps us understand the learned communication protocol by investigating the attention weights associated with each message symbol and the alignment of attention weights between Speaker and Listener agents. Overall, our results suggest that attention is a promising mechanism for developing more human-like emergent language.