Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agents

TL;DR

This paper demonstrates that communication among neural-network agents leads to the emergence of Differential Case Marking, highlighting the importance of interaction in language evolution, supported by multi-agent reinforcement learning simulations.

Contribution

It shows that neural-network agents develop Differential Case Marking only through communication, not just learning, advancing understanding of language emergence mechanisms.

Findings

Communication induces DCM in agents

Learning alone does not produce DCM

Supports role of communication in language evolution

Abstract

Differential Case Marking (DCM) refers to the phenomenon where grammatical case marking is applied selectively based on semantic, pragmatic, or other factors. The emergence of DCM has been studied in artificial language learning experiments with human participants, which were specifically aimed at disentangling the effects of learning from those of communication (Smith & Culbertson, 2020). Multi-agent reinforcement learning frameworks based on neural networks have gained significant interest to simulate the emergence of human-like linguistic phenomena. In this study, we employ such a framework in which agents first acquire an artificial language before engaging in communicative interactions, enabling direct comparisons to human result. Using a very generic communication optimization algorithm and neural-network learners that have no prior experience with language or semantic preferences, our results demonstrate that learning alone does not lead to DCM, but when agents communicate, differential use of markers arises. This supports Smith and Culbertson (2020)'s findings that highlight the critical role of communication in shaping DCM and showcases the potential of neural-agent models to complement experimental research on language evolution.