Evaluating the Robustness of Neural Language Models to Input Perturbations
This addresses the issue of overestimating model reliability in NLP for researchers and practitioners, though it is incremental as it highlights an existing concern without proposing a new solution.
The study tackled the problem of neural language models being unreliable with noisy real-world data by testing their robustness to input perturbations, finding that models like BERT and RoBERTa are sensitive to small changes, with performance decreasing significantly.
High-performance neural language models have obtained state-of-the-art results on a wide range of Natural Language Processing (NLP) tasks. However, results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data. In this study, we design and implement various types of character-level and word-level perturbation methods to simulate realistic scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained. Conducting comprehensive experiments on different NLP tasks, we investigate the ability of high-performance language models such as BERT, XLNet, RoBERTa, and ELMo in handling different types of input perturbations. The results suggest that language models are sensitive to input perturbations and their performance can decrease even when small changes are introduced. We highlight that models need to be further improved and that current benchmarks are not reflecting model robustness well. We argue that evaluations on perturbed inputs should routinely complement widely-used benchmarks in order to yield a more realistic understanding of NLP systems robustness.