English

Syntactic Structure from Deep Learning

Computation and Language 2020-04-24 v1

Abstract

Modern deep neural networks achieve impressive performance in engineering applications that require extensive linguistic skills, such as machine 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 long-standing 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.

Keywords

Cite

@article{arxiv.2004.10827,
  title  = {Syntactic Structure from Deep Learning},
  author = {Tal Linzen and Marco Baroni},
  journal= {arXiv preprint arXiv:2004.10827},
  year   = {2020}
}

Comments

In press at Annual Reviews of Linguistics

R2 v1 2026-06-23T15:02:18.132Z