有效消息传递和输入可变性对神经代理迭代语言学习的影响
The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning
摘要:
自然语言在表达句法结构的不同策略(如词序或词形变化)之间显示出权衡。然而,这种权衡在最近用神经网络代理进行的迭代语言学习的模拟中还没有出现(Chaabouni等人,2019年b)。我们根据在语言进化领域的可比实验中起重要作用的三个因素重新评估了这一结果:(i)说话者对有效消息传递的偏见,(ii)非系统输入语言,(iii)学习瓶颈。我们的模拟表明,神经代理主要致力于保持在学习过程中观察到的话语类型分布,而不是开发更有效或更系统的语言。
英文摘要:
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.
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。