Local Structure Matters Most: Perturbation Study in NLU
This work addresses the robustness and interpretability of natural language understanding models for researchers and practitioners, though it is incremental as it builds on prior perturbation studies.
The study investigated how neural language models rely on local versus global text structure by applying perturbations to word, subword, and character order, finding that models primarily depend on local structure and make limited use of global ordering, with performance changes quantified through empirical experiments.
Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations has shown that neural models are surprisingly insensitive to the order of words. In this paper, we investigate this phenomenon by developing order-altering perturbations on the order of words, subwords, and characters to analyze their effect on neural models' performance on language understanding tasks. We experiment with measuring the impact of perturbations to the local neighborhood of characters and global position of characters in the perturbed texts and observe that perturbation functions found in prior literature only affect the global ordering while the local ordering remains relatively unperturbed. We empirically show that neural models, invariant of their inductive biases, pretraining scheme, or the choice of tokenization, mostly rely on the local structure of text to build understanding and make limited use of the global structure.