Communication is one of the most impressive human abilities but historically it has been studied in machine learning on confined datasets of natural language, and by various other fields in simple low-dimensional spaces. Recently, with the rise of deep RL methods, the questions around the emergence of communication can now be studied in new, complex multi-agent scenarios. Two previous successful workshops (2017, 2018) have gathered the community to discuss how, when, and to what end communication emerges, producing research that was later published at top ML venues such as ICLR, ICML, AAAI. Now, we wish to extend these ideas and explore a new direction: how emergent communication can become more like natural language, and what natural language understanding can learn from emergent communication.

The push towards emergent natural language is a necessary and important step in all facets of the field. For studying the evolution of human language, emerging a natural language can uncover the requirements that spurred crucial aspects of language (e.g. compositionality). When emerging communication for multi-agent scenarios, protocols may be sufficient for machine-machine interactions, but emerging a natural language is necessary for human-machine interactions. Finally, it may be possible to have truly general natural language understanding if agents learn the language through interaction as humans do. To make this progress, it is necessary to close the gap between artificial and natural language learning.

To tackle this problem, we want to take an interdisciplinary approach by inviting researchers from various fields (machine learning, game theory, evolutionary biology, linguistics, cognitive science, and programming languages) to participate and engaging them to unify the differing perspectives. Providing this platform, we hope that not only will the ML community will learn something new, but other fields can also gain a new perspective and see the potential of ML as a powerful experimental paradigm for themselves. We believe that the third iteration of this workshop with a novel, unexplored goal and strong commitment to diversity will allow this burgeoning field to flourish.

• Ted Gibson (MIT)
• Jacob Andreas (MIT/Microsoft Semantic Machines)
• Stefan Lee (OSU)
• Noga Zaslavsky (MIT)
• Jason Eisner (JHU/Microsoft Semantic Machines)