Syntactic Structure from Deep Learning

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.

In press at Annual Reviews of Linguistics

References in corpus (2)

• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• Attention-over-Attention Neural Networks for Reading Comprehension

Cited by in corpus (9)

• Modeling morphology with Linear Discriminative Learning: considerations and design choices
• Scope Ambiguities in Large Language Models
• Artificial intelligence contribution to translation industry: looking back and forward
• What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure
• What fifty-one years of Linguistics and Artificial Intelligence research tell us about their correlation: A scientometric analysis
• The boundaries of meaning: a case study in neural machine translation
• Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations
• Do Large Language Models know who did what to whom?
• Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model