The king is naked: On the notion of robustness for natural language processing

Conference item

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.

Authors: La Malfa, E; Kwiatkowska, M

• Publication status: Published
• Publisher: Association for the Advancement of Artificial Intelligence
• Journal: Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence
• Volume: 36
• Issue: 10
• Pages: 11047-11057
• Publication date: 2022-06-28
• Acceptance date: 2021-12-01
• DOI: 10.1609/aaai.v36i10.21353
• Language: English
• Keywords: FFR