A Review of the Applications of Deep Learning-Based Emergent Communication

TL;DR

This paper reviews how emergent communication in deep multi-agent reinforcement learning can be applied across various scientific and technological fields, highlighting current research and future directions.

Contribution

It provides a comprehensive overview of emergent communication applications in machine learning, NLP, linguistics, and cognitive science, emphasizing its interdisciplinary relevance.

Findings

Emergent communication aids in understanding language development.

Applications span multiple scientific disciplines.

Future research directions are identified for advancing the field.

Abstract

Emergent communication, or emergent language, is the field of research which studies how human language-like communication systems emerge de novo in deep multi-agent reinforcement learning environments. The possibilities of replicating the emergence of a complex behavior like language have strong intuitive appeal, yet it is necessary to complement this with clear notions of how such research can be applicable to other fields of science, technology, and engineering. This paper comprehensively reviews the applications of emergent communication research across machine learning, natural language processing, linguistics, and cognitive science. Each application is illustrated with a description of its scope, an explication of emergent communication's unique role in addressing it, a summary of the extant literature working towards the application, and brief recommendations for near-term research directions.