Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer

摘要

The robustness of pretrained language models (PLMs) is generally measured using performance drops on two or more domains. However, we do not yet understand the inherent robustness achieved by contributions from different layers of a PLM. We systematically analyze the robustness of these representations layer by layer from two perspectives. First, we measure the robustness of representations by using domain divergence between two domains. We find that ⅰ) Domain variance increases from the lower to the upper layers for vanilla PLMs; ⅱ) Models continuously pretrained on domain-specific data (DAPT) (Gururangan ct al., 2020) exhibit more variance than their pretrained PLM counterparts: and that ⅲ) Distilled models (e.g.,DistilBERT) also show greater domain variance. Second, we investigate the robustness of representations by analyzing the encoded syntactic and semantic information using diagnostic probes. We find that similar layers have similar amounts of linguistic information for data from an unseen domain.