Internal and external pressures on language emergence: least effort, object constancy and frequency
This work addresses the challenge of making artificial agents' emergent languages more natural-like, which is incremental as it builds on prior referential game research.
The paper tackled the problem that emergent communication protocols in referential games lack features of natural languages like compositionality, by introducing pressures such as least effort and object constancy variants; the result was languages with less redundancy, more focus on high-level concepts, and better generalization, reducing the gap to natural languages.
In previous work, artificial agents were shown to achieve almost perfect accuracy in referential games where they have to communicate to identify images. Nevertheless, the resulting communication protocols rarely display salient features of natural languages, such as compositionality. In this paper, we propose some realistic sources of pressure on communication that avert this outcome. More specifically, we formalise the principle of least effort through an auxiliary objective. Moreover, we explore several game variants, inspired by the principle of object constancy, in which we alter the frequency, position, and luminosity of the objects in the images. We perform an extensive analysis on their effect through compositionality metrics, diagnostic classifiers, and zero-shot evaluation. Our findings reveal that the proposed sources of pressure result in emerging languages with less redundancy, more focus on high-level conceptual information, and better abilities of generalisation. Overall, our contributions reduce the gap between emergent and natural languages.