Searching for the Most Human-like Emergent Language
This work addresses the challenge of creating more human-like artificial languages for researchers in emergent communication, though it is incremental as it builds on existing methods with optimization.
The paper tackles the problem of generating emergent languages that are similar to human language by using a signalling game-based environment with hyperparameter optimization, achieving state-of-the-art results in terms of statistical similarity as measured by XferBench.
In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of emergent language as well as corroborate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language.