3 accepted papers
Data-efficient training requires strong inductive biases. To the extent that transformer attention matrices encode syntactic relationships, we would predict that knowledge distillation (KD) targeting attention should selectively accelerate syntax acquisition relative to conventional logit-based KD.
Accounts of human language processing have long appealed to implicit “situation models” that enrich comprehension with relevant but unstated world knowledge. Here, we apply causal intervention techniques to recent transformer models to analyze performance on the Winograd Schema Challenge (WSC), wher…
Sampling is a promising bottom-up method for exposing what generative models have learned about language, but it remains unclear how to generate representative samples from popular masked language models (MLMs) like BERT. The MLM objective yields a dependency network with no guarantee of consistent…