Natural languages display a trade-off among different strategies to convey
syntactic structure, such as word order or inflection. This trade-off, however,
has not appeared in recent simulations of iterated language learning with
neural network agents (Chaabouni et al., 2019b). We re-evaluate this result in
light of three factors that play an important role in comparable experiments
from the Language Evolution field: (i) speaker bias towards efficient
messaging, (ii) non systematic input languages, and (iii) learning bottleneck.
Our simulations show that neural agents mainly strive to maintain the utterance
type distribution observed during learning, instead of developing a more
efficient or systematic language.

该研究发现，在使用神经网络代理进行迭代语言学习的近期模拟中，并不存在诸如词序或屈折等表达句法结构的不同策略间的权衡。然而，这一研究发现在考虑到偏向于高效传达、不系统的输入语言和学习瓶颈等三个因素后得到了重新评估，并发现神经网络代理主要努力保持学习期间观察到的话语类型分布，而不是发展更高效或系统化的语言。