The King Is Naked: On the Notion of Robustness for Natural Language Processing

Authors

  • Emanuele La Malfa University of Oxford
  • Marta Kwiatkowska University of Oxford

DOI:

https://doi.org/10.1609/aaai.v36i10.21353

Keywords:

Speech & Natural Language Processing (SNLP), Philosophy And Ethics Of AI (PEAI)

Abstract

There is growing evidence that the classical notion of adversarial robustness originally introduced for images has been adopted as a de facto standard by a large part of the NLP research community. We show that this notion is problematic in the context of NLP as it considers a narrow spectrum of linguistic phenomena. In this paper, we argue for semantic robustness, which is better aligned with the human concept of linguistic fidelity. We characterize semantic robustness in terms of biases that it is expected to induce in a model. We study semantic robustness of a range of vanilla and robustly trained architectures using a template-based generative test bed. We complement the analysis with empirical evidence that, despite being harder to implement, semantic robustness can improve performance %gives guarantees for on complex linguistic phenomena where models robust in the classical sense fail.

Downloads

Published

2022-06-28

How to Cite

Malfa, E. L., & Kwiatkowska, M. (2022). The King Is Naked: On the Notion of Robustness for Natural Language Processing. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11047-11057. https://doi.org/10.1609/aaai.v36i10.21353

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing