P.STAR: Parameter-free Structure Analysis via Reordering for Lossless Visualization of Layers in Language Models

We introduce P.STAR: a new parameter-free method that can be used to inspect the embedding space of a set of instance representations (e.g. words in context) across layers of a contextualized language model at one glance and without loss of information. We use a matrix reordering approach that relies on signature distances; instances are represented in terms of their distances to all other instances in the set. The reordered matrix of signature representations provides a visual depiction of how structures emerge across layers of a contextualized model. We validate our approach by comparing how words in context are grouped to their PoS and Sense labels in two annotated datasets. In line with previous research, we observe that lower-layer representations emphasize PoS-information while higher layers group instances on the basis of senses. We also show that our reordering approach can identify errors in the labels.