What can linguistics and deep learning contribute to each other?

TL;DR

This paper advocates for a bidirectional collaboration between linguistics and deep learning, emphasizing how each field can inform and improve the other through targeted experiments and modeling.

Contribution

It highlights specific ways linguistics and neural network research can mutually benefit, including experimental paradigms and modeling approaches.

Findings

Linguists can define clear linguistic capabilities for neural networks.

Neural networks can model human sentence processing.

Both fields can evaluate innate language constraints.

Abstract

Joe Pater's target article calls for greater interaction between neural network research and linguistics. I expand on this call and show how such interaction can benefit both fields. Linguists can contribute to research on neural networks for language technologies by clearly delineating the linguistic capabilities that can be expected of such systems, and by constructing controlled experimental paradigms that can determine whether those desiderata have been met. In the other direction, neural networks can benefit the scientific study of language by providing infrastructure for modeling human sentence processing and for evaluating the necessity of particular innate constraints on language acquisition.