Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
This work addresses the problem of making emergent communication languages more natural for computational linguistics, though it is incremental as it builds on existing frameworks.
The paper reinterprets Lewis's signaling game as a beta-VAE to clarify how prior distributions affect emergent languages, showing that appropriate priors lead to more natural word lengths and segments, while conventional methods prevent adherence to Zipf's law of abbreviation and Harris's articulation scheme.
As a sub-discipline of evolutionary and computational linguistics, emergent communication (EC) studies communication protocols, called emergent languages, arising in simulations where agents communicate. A key goal of EC is to give rise to languages that share statistical properties with natural languages. In this paper, we reinterpret Lewis's signaling game, a frequently used setting in EC, as beta-VAE and reformulate its objective function as ELBO. Consequently, we clarify the existence of prior distributions of emergent languages and show that the choice of the priors can influence their statistical properties. Specifically, we address the properties of word lengths and segmentation, known as Zipf's law of abbreviation (ZLA) and Harris's articulation scheme (HAS), respectively. It has been reported that the emergent languages do not follow them when using the conventional objective. We experimentally demonstrate that by selecting an appropriate prior distribution, more natural segments emerge, while suggesting that the conventional one prevents the languages from following ZLA and HAS.