NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication

TL;DR

NeLLCom-X extends neural-agent frameworks to simulate language learning and group communication, revealing how interaction and group size influence linguistic properties and evolution.

Contribution

It introduces realistic role-alternating agents and group communication into the NeLLCom framework, enabling more comprehensive studies of language emergence.

Findings

Replicated key findings on word-order/case-marking trade-off.

Showed interaction influences linguistic convergence.

Demonstrated the importance of group dynamics in language evolution.

Abstract

Recent advances in computational linguistics include simulating the emergence of human-like languages with interacting neural network agents, starting from sets of random symbols. The recently introduced NeLLCom framework (Lian et al., 2023) allows agents to first learn an artificial language and then use it to communicate, with the aim of studying the emergence of specific linguistics properties. We extend this framework (NeLLCom-X) by introducing more realistic role-alternating agents and group communication in order to investigate the interplay between language learnability, communication pressures, and group size effects. We validate NeLLCom-X by replicating key findings from prior research simulating the emergence of a word-order/case-marking trade-off. Next, we investigate how interaction affects linguistic convergence and emergence of the trade-off. The novel framework facilitates future simulations of diverse linguistic aspects, emphasizing the importance of interaction and group dynamics in language evolution.