Search Results for author:
Found 4 papers, 3 papers with code
Probing BERT’s priors with serial reproduction chains
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.
Causal interventions expose implicit situation models for commonsense language understanding
Accounts of human language processing have long appealed to implicit ``situation models'' that enrich comprehension with relevant but unstated world knowledge.
Probing BERT's priors with serial reproduction chains
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.
Investigating representations of verb bias in neural language models
Languages typically provide more than one grammatical construction to express certain types of messages.
