Incorporating Pragmatic Reasoning Communication into Emergent Language

TL;DR

This paper integrates pragmatic reasoning into emergent language models to improve naturalness, accuracy, and robustness of communication in multi-agent systems and complex environments like Starcraft II.

Contribution

It introduces computational models combining short-term pragmatic reasoning with long-term emergent language, evaluated through referential games and Starcraft II.

Findings

Pragmatic reasoning enhances naturalness and accuracy of emergent language.

Models with mutual reasoning outperform baseline approaches.

Results demonstrate improved robustness and succinctness in communication.

Abstract

Emergentism and pragmatics are two research fields that study the dynamics of linguistic communication along substantially different timescales and intelligence levels. From the perspective of multi-agent reinforcement learning, they correspond to stochastic games with reinforcement training and stage games with opponent awareness. Given that their combination has been explored in linguistics, we propose computational models that combine short-term mutual reasoning-based pragmatics with long-term language emergentism. We explore this for agent communication referential games as well as in Starcraft II, assessing the relative merits of different kinds of mutual reasoning pragmatics models both empirically and theoretically. Our results shed light on their importance for making inroads towards getting more natural, accurate, robust, fine-grained, and succinct utterances.