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.

本文在认知科学的迭代学习理论的基础上，探索利用串行复制链从 BERT 先验中抽取样本，发现 Generative Stochastic Network（GSN）采样器是地面真实联合分布的唯一一致估计器，其从 GSN 链产生的句子的词汇和句法统计数据与地面真实语料库分布密切匹配，并在大量自然性判断中表现比其他方法更好，从而为从底层开始探测创新奠定了更牢固的理论基础。