Research Area:  Machine Learning

Abstract:

The ability to cooperate through language is a defining feature of humans. As the perceptual, motory and planning capabilities of deep artificial networks increase, researchers are studying whether they also can develop a shared language to interact. From a scientific perspective, understanding the conditions under which language evolves in communities of deep agents and its emergent features can shed light on human language evolution. From an applied perspective, endowing deep networks with the ability to solve problems interactively by communicating with each other and with us should make them more flexible and useful in everyday life.This article surveys representative recent language emergence studies from both of these two angles.

Keywords:  
Multi-Agent Communication
deep artificial networks
Deep Learning

Author(s) Name:  Angeliki Lazaridou, Marco Baroni

Publisher name:  arXiv:2006.02419

DOI:  10.48550/arXiv.2006.02419

Volume Information:  

Paper Link:   https://arxiv.org/abs/2006.02419