Syntactic Structure from Deep Learning
Syntactic Structure from Deep Learning
复制标题
DOI：
10.1146/annurev-linguistics-032020-051035
复制
发表时间：
2021-01-01
期刊：
影响因子：
--
通讯作者：
Baroni, Marco
中科院分区：
文献类型：
--
作者：
Linzen, Tal;Baroni, Marco
现代深度神经网络在需要广泛语言技能的工程应用中取得了令人印象深刻的性能，例如机器翻译。这一成功引发了人们对探索这些模型是否能从它们接触到的原始数据中诱导出类似人类的语法知识的兴趣，因此，它们是否能为关于语言习得所需的先天结构的长期争论提供新的线索。在这篇文章中，我们回顾了深度网络句法能力的代表性研究，并讨论了这项工作对理论语言学的更广泛影响。
Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such asmachine translation. This success has sparked interest in probing whether these models are inducing human-like grammatical knowledge from the raw data they are exposed to and, consequently, whether they can shed new light on longstanding debates concerning the innate structure necessary for language acquisition. In this article, we survey representative studies of the syntactic abilities of deep networks and discuss the broader implications that this work has for theoretical linguistics.