Emergence of Compositional Language with Deep Generational Transmission

Michael Cogswell, Jiasen Lu, Stefan Lee, Devi Parikh, Dhruv Batra

TL;DR: We use cultural transmission to encourage compositionality in languages that emerge from interactions between neural agents.

Abstract: Recent work has studied the emergence of language among deep reinforcement learning agents that must collaborate to solve a task. Of particular interest are the factors that cause language to be compositional---i.e., express meaning by combining words which themselves have meaning. Evolutionary linguists have found that in addition to structural priors like those already studied in deep learning, the dynamics of transmitting language from generation to generation contribute significantly to the emergence of compositionality. In this paper, we introduce these cultural evolutionary dynamics into language emergence by periodically replacing agents in a population to create a knowledge gap, implicitly inducing cultural transmission of language. We show that this implicit cultural transmission encourages the resulting languages to exhibit better compositional generalization.

Keywords: Cultural Evolution, Deep Learning, Language Emergence

Code: [ mcogswell/evolang](https://github.com/mcogswell/evolang)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1904.09067/code)