arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.12982cs.MA
收藏

论群体异质性在突发传播中的作用

On the role of population heterogeneity in emergent communication

Mathieu Rita, Florian Strub, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux

摘要:

人口通常被认为是语言出现和发展的结构性组成部分:人口越多,语言的结构性就越强。虽然这种观察在社会语言学文献中很普遍,但它并没有在神经代理的计算机模拟中得到一致的再现。因此,在本文中,我们的目的是澄清这一明显的矛盾。我们探索新兴的语言特性,通过不同的代理人口规模的扬声器-听众刘易斯游戏。在再现实验差异后,我们挑战了代理社区是同质的模拟假设。我们首先研究了说话者-听者不对称如何改变语言结构,以考察两个潜在的多样性因素:训练速度和网络容量。我们发现,新兴的语言属性只改变了相对差异的学习速度在说话者和听话者之间,而不是由他们的绝对值。从那时起,我们利用这一观察结果来控制人口异质性,而不引入混杂因素。最后,我们证明了引入这种训练速度异质性自然会解决最初的矛盾:更大的模拟社区开始开发更稳定和结构化的语言。

英文摘要:

Populations have often been perceived as a structuring component for language to emerge and evolve: the larger the population, the more structured the language. While this observation is widespread in the sociolinguistic literature, it has not been consistently reproduced in computer simulations with neural agents. In this paper, we thus aim to clarify this apparent contradiction. We explore emergent language properties by varying agent population size in the speaker-listener Lewis Game. After reproducing the experimental difference, we challenge the simulation assumption that the agent community is homogeneous. We first investigate how speaker-listener asymmetry alters language structure to examine two potential diversity factors: training speed and network capacity. We find out that emergent language properties are only altered by the relative difference of learning speeds between speaker and listener, and not by their absolute values. From then, we leverage this observation to control population heterogeneity without introducing confounding factors. We finally show that introducing such training speed heterogeneities naturally sort out the initial contradiction: larger simulated communities start developing more stable and structured languages.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑