Why Robust Natural Language Understanding is a Challenge
This work addresses robustness issues in NLU for AI safety and reliability, but it is incremental as it adapts existing verification methods from computer vision to a new domain.
The paper tackles the challenge of verifying robustness in Natural Language Understanding classification by proposing a verification specification based on larger regions of interest, but finds that the verifier struggles to output positive results despite the data being almost linearly separable.
With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks notoriously present low robustness and can be highly sensitive to small input perturbations. Recently, many methods for verifying networks' general properties of robustness have been proposed, but they are mostly applied in Computer Vision. In this paper we propose a Verification specification for Natural Language Understanding classification based on larger regions of interest, and we discuss the challenges of such task. We observe that, although the data is almost linearly separable, the verifier struggles to output positive results and we explain the problems and implications.