We investigate the extent to which individual attention heads in pretrained
transformer language models, such as BERT and RoBERTa, implicitly capture
syntactic dependency relations. We employ two methods---taking the maximum
attention weight and computing the maximum spanning tree---to extract implicit
dependency relations from the attention weights of each layer/head, and compare
them to the ground-truth Universal Dependency (UD) trees. We show that, for
some UD relation types, there exist heads that can recover the dependency type
significantly better than baselines on parsed English text, suggesting that
some self-attention heads act as a proxy for syntactic structure. We also
analyze BERT fine-tuned on two datasets---the syntax-oriented CoLA and the
semantics-oriented MNLI---to investigate whether fine-tuning affects the
patterns of their self-attention, but we do not observe substantial differences
in the overall dependency relations extracted using our methods. Our results
suggest that these models have some specialist attention heads that track
individual dependency types, but no generalist head that performs holistic
parsing significantly better than a trivial baseline, and that analyzing
attention weights directly may not reveal much of the syntactic knowledge that
BERT-style models are known to learn.

本研究探讨预训练变形金刚语言模型中的注意头在多大程度上隐含捕获了句法依赖关系，并使用两种方法提取每层 / 头 attention 权重中的隐含依赖关系，比较它们与基准 UD 树的差异。结果表明，这些模型有一些跟踪特定依赖类型的专业注意头，但没有表现出比浅显的基准模型更好的整体解析能力。同时，注意权重直接分析不能揭示 BERT-Style 模型已知的语法知识。