Evaluating the Robustness of Neural Language Models to Input Perturbations

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1558–1570 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 1558 Abstract 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. 1 Introduction High-performance deep neural language models such as BERT (Devlin et al., 2018), XLNet (Z. 1 https://rajpurkar.github.io/SQuAD- explorer/ Yang et al., 2019), and GPT-2 (Radford et al., 2019) have brought breakthroughs to a wide range of Natural Language Processing (NLP) tasks including text classification, sentiment analysis, textual entailment, natural language inference, machine translation, and question answering. Their immense ability in capturing various linguistic properties has led these state-of-the-art language models to master different NLP tasks, even surpassing human accuracy on some benchmarks such as SQuAD1. However, recent studies have revealed that there is a gap between performing well on benchmarks and actually working under real-world situations (Belinkov and Bisk, 2018; Ribeiro et al., 2020). Even a well-trained, high-performance deep language model can be sensitive to negligible changes in the input that cause the model to make erroneous decisions (M. Sun et al., 2018). This raises serious concerns regarding the robustness/reliability of neural language models utilized in real-world applications. The terms ‘robustness’ and ‘reliability’ refer to the ability of a system to perform consistently well in situations where changes to input should not cause a change in the system’s output, or the system is expected to properly reflect the change and produce a correct outcome. Applying automatic or human-controlled perturbations to textual inputs has been shown to be effective for evaluating the robustness of NLP systems, investigating their vulnerabilities, and finding their bugs. Recently, CheckList (Ribeiro et al., 2020) provided a framework for behavioral testing of NLP systems inspired by black-box Evaluating the Robustness of Neural Language Models to Input Perturbations Milad Moradi, Matthias Samwald Institute for Artificial Intelligence Medical University of Vienna, Austria {milad.moradivastegani, matthias.samwald}@meduniwien.ac.at 1559 testing in software engineering. CheckList enabled generating new (perturbed) test samples through abstracting different test types aimed at testing linguistic capabilities. Other studies focused on evaluating robustness …

Content truncated to 500 words