Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers

TL;DR

This paper investigates how different sub-layers of a pre-trained language model encode contextual information for polysemous words, revealing that high contextualization in top layers is context-dependent and not uniform.

Contribution

It introduces a detailed probing methodology to localize contextualization strength across PLM sub-layers, focusing on polysemous words and varying context lengths.

Findings

High contextualization in top sub-layers for specific word positions

Context length and richness influence the degree of contextualization

Contextualization does not systematically generalize across positions

Abstract

In the era of high performing Large Language Models, researchers have widely acknowledged that contextual word representations are one of the key drivers in achieving top performances in downstream tasks. In this work, we investigate the degree of contextualization encoded in the fine-grained sub-layer representations of a Pre-trained Language Model (PLM) by empirical experiments using linear probes. Unlike previous work, we are particularly interested in identifying the strength of contextualization across PLM sub-layer representations (i.e. Self-Attention, Feed-Forward Activation and Output sub-layers). To identify the main contributions of sub-layers to contextualisation, we first extract the sub-layer representations of polysemous words in minimally different sentence pairs, and compare how these representations change through the forward pass of the PLM network. Second, by probing on a sense identification classification task, we try to empirically localize the strength of contextualization information encoded in these sub-layer representations. With these probing experiments, we also try to gain a better understanding of the influence of context length and context richness on the degree of contextualization. Our main conclusion is cautionary: BERT demonstrates a high degree of contextualization in the top sub-layers if the word in question is in a specific position in the sentence with a shorter context window, but this does not systematically generalize across different word positions and context sizes.