Unsupervised Translation of Emergent Communication

TL;DR

This paper explores using unsupervised neural machine translation to interpret emergent communication among agents, revealing how task complexity influences the translatability of EC without relying on parallel data.

Contribution

It introduces the first method to translate emergent communication without parallel data, linking task complexity and semantic diversity to translation success.

Findings

UNMT can successfully translate EC.

Semantic diversity improves EC translatability.

High task complexity with constrained semantics yields pragmatic EC.

Abstract

Emergent Communication (EC) provides a unique window into the language systems that emerge autonomously when agents are trained to jointly achieve shared goals. However, it is difficult to interpret EC and evaluate its relationship with natural languages (NL). This study employs unsupervised neural machine translation (UNMT) techniques to decipher ECs formed during referential games with varying task complexities, influenced by the semantic diversity of the environment. Our findings demonstrate UNMT's potential to translate EC, illustrating that task complexity characterized by semantic diversity enhances EC translatability, while higher task complexity with constrained semantic variability exhibits pragmatic EC, which, although challenging to interpret, remains suitable for translation. This research marks the first attempt, to our knowledge, to translate EC without the aid of parallel data.