3 papers
cs.CL2021
Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning
Forrest Davis, Marten van Schijndel
A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in…
cs.CL2020
Discourse structure interacts with reference but not syntax in neural language models
Forrest Davis, Marten van Schijndel
Language models (LMs) trained on large quantities of text have been claimed to acquire abstract linguistic representations. Our work tests the robustness of these abstractions by f…
cs.CL2020
Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment
Forrest Davis, Marten van Schijndel
A standard approach to evaluating language models analyzes how models assign probabilities to valid versus invalid syntactic constructions (i.e. is a grammatical sentence more prob…