On the proper role of linguistically-oriented deep net analysis in linguistic theorizing
This work aims to clarify the role of deep net analysis in linguistics, potentially offering a new theoretical approach, but it is incremental as it builds on existing experimental methods.
The paper addresses the unclear implications of linguistically-oriented deep net analysis for linguistic theorizing, proposing to treat deep networks as theories predicting utterance acceptability to gain a complementary theoretical tool.
A lively research field has recently emerged that uses experimental methods to probe the linguistic behavior of modern deep networks. While work in this tradition often reports intriguing results about the grammatical skills of deep nets, it is not clear what their implications for linguistic theorizing should be. As a consequence, linguistically-oriented deep net analysis has had very little impact on linguistics at large. In this chapter, I suggest that deep networks should be treated as theories making explicit predictions about the acceptability of linguistic utterances. I argue that, if we overcome some obstacles standing in the way of seriously pursuing this idea, we will gain a powerful new theoretical tool, complementary to mainstream algebraic approaches.