On the proper role of linguistically-oriented deep net analysis in linguistic theorizing

A lively research field has recently emerged that uses experimental methods probe the linguistic behavior of modern deep networks. While work in this often reports intriguing results about the grammatical skills of deep, it is not clear what their implications for linguistic theorizing should. As a consequence, linguistically-oriented deep net analysis has had very impact on linguistics at large. In this chapter, I suggest that deep should be treated as theories making explicit predictions about the of linguistic utterances. I argue that, if we overcome some standing in the way of seriously pursuing this idea, we will gain a new theoretical tool, complementary to mainstream algebraic.