Learning Compositional Negation in Populations of Roth-Erev and Neural Agents

by   Graham Todd, et al.

Agent-based models and signalling games are useful tools with which to study the emergence of linguistic communication in a tractable setting. These techniques have been used to study the compositional property of natural languages, but have been limited in how closely they model real communicators. In this work, we present a novel variant of the classic signalling game that explores the learnability of simple compositional rules concerning negation. The approach builds on the work of Steinert-Threlkeld (2016) by allowing agents to determine the identity of the "function word" representing negation while simultaneously learning to assign meanings to atomic symbols. We extend the analysis with the introduction of a population of concurrently communicating agents, and explore how the complications brought about by a larger population size affect the type and stability of the signalling systems learned. We also relax assumptions of the parametric form of the learning agents and examine how neural network-based agents optimized through reinforcement learning behave under various task settings. We find that basic compositional properties are robustly learnable across a wide range of model relaxations and agent instantiations.


page 1

page 2

page 3

page 4


The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents

Since first introduced, computer simulation has been an increasingly imp...

On the Correspondence between Compositionality and Imitation in Emergent Neural Communication

Compositionality is a hallmark of human language that not only enables l...

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

The ability of algorithms to evolve or learn (compositional) communicati...

Emergence of Grounded Compositional Language in Multi-Agent Populations

By capturing statistical patterns in large corpora, machine learning has...

Emergence of Compositional Language with Deep Generational Transmission

Consider a collaborative task that requires communication. Two agents ar...

Spatial community structure impedes language amalgamation in a population-based iterated learning model

The iterated learning model is an agent-based model of language evolutio...

On the Spontaneous Emergence of Discrete and Compositional Signals

We propose a general framework to study language emergence through signa...

Please sign up or login with your details

Forgot password? Click here to reset