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. The MLM objective yields a dependency network with no guarantee of consistent conditional distributions, posing a problem for naive approaches. Drawing from theories of iterated learning in cognitive science, we explore the use of serial reproduction chains to sample from BERT’s priors. In particular, we observe that a unique and consistent estimator of the ground-truth joint distribution is given by a Generative Stochastic Network (GSN) sampler, which randomly selects which token to mask and reconstruct on each step. We show that the lexical and syntactic statistics of sentences from GSN chains closely match the ground-truth corpus distribution and perform better than other methods in a large corpus of naturalness judgments. Our findings establish a firmer theoretical foundation for bottom-up probing and highlight richer deviations from human priors.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
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…
Language ModellingMasked Language ModelingProbing BERT’s priors with serial reproduction chains
We can learn as much about language models from what they say as we learn from their performance on targeted benchmarks. Sampling is a promising bottom-up method for probing, but generating samples from successful models…
Language ModelingLanguage ModellingMasked Language ModelingComparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
Humans extract useful abstractions of the world from noisy sensory data. Serial reproduction allows us to study how people construe the world through a paradigm similar to the game of telephone, where one person observes…
Evaluating Models of Robust Word Recognition with Serial Reproduction
Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received l…
How memory biases affect information transmission: A rational analysis of serial reproduction
Many human interactions involve pieces of information being passed from one person to another, raising the question of how this process of information transmission is affected by the capacities of the agents involved. In…