Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?
This addresses the problem of PLM susceptibility to noise in subword segmentation for NLP researchers, but it is incremental as it builds on existing concerns about segmentation and noise.
The study assessed the robustness of pretrained language models (PLMs) against disrupted subword segmentation caused by noise, finding that PLMs fail to accurately compute word meanings when noise introduces completely different subwords, small fragments, or many additional subwords, especially within other subwords.
For Pretrained Language Models (PLMs), their susceptibility to noise has recently been linked to subword segmentation. However, it is unclear which aspects of segmentation affect their understanding. This study assesses the robustness of PLMs against various disrupted segmentation caused by noise. An evaluation framework for subword segmentation, named Contrastive Lexical Semantic (CoLeS) probe, is proposed. It provides a systematic categorization of segmentation corruption under noise and evaluation protocols by generating contrastive datasets with canonical-noisy word pairs. Experimental results indicate that PLMs are unable to accurately compute word meanings if the noise introduces completely different subwords, small subword fragments, or a large number of additional subwords, particularly when they are inserted within other subwords.