Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive biases on both the training framework and the data are needed to develop a compositional communication. Moreover, we prove that compositionality spontaneously arises in the signaling games, where agents communicate over a noisy channel. We experimentally confirm that a range of noise levels, which depends on the model and the data, indeed promotes compositionality. Finally, we provide a comprehensive study of this dependence and report results in terms of recently studied compositionality metrics: topographical similarity, conflict count, and context independence.

翻译：如果复杂的信号可以作为更简单的分部分的组合来表示,则通信即为构成。在本文中,我们理论上表明,为了发展一种组成交流,需要从培训框架和数据两方面提出偏差。此外,我们还证明,在信号游戏中自发地产生组成性,代理商通过一个吵闹的频道进行交流。我们实验性地确认,一系列噪音水平,取决于模型和数据,确实促进了构成性。最后,我们对这种依赖性进行了全面研究,并报告了最近研究的构成性衡量标准的结果:地形相似性、冲突计数和背景独立性。