mlsanityData to 7 Oct 2026

Why Robust Natural Language Understanding is a Challenge

arXiv 2206.14575 ↗First posted 21 Jun 2022cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

30 of 51 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  9. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  10. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  11. 2016Safety Verification of Deep Neural Networkscited by 262
  12. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
18 more
  1. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  2. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  3. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
  4. 2021Anticipating Safety Issues in E2E Conversational AI: Framework and Toolingcited by 77
  5. 2020Robustness Verification for Transformerscited by 76
  6. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
  7. 2020Very Deep Transformers for Neural Machine Translationcited by 50
  8. 2018Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledgecited by 45
  9. 2020Emergence of Separable Manifolds in Deep Language Representationscited by 39
  10. 2021Neural Network Robustness as a Verification Property: A Principled Case Studycited by 35
  11. 2018Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classificationcited by 34
  12. 2021Certified Robustness to Programmable Transformations in LSTMscited by 18
  13. 2021The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identitycited by 16
  14. 2020Word Shape Matters: Robust Machine Translation with Visual Embeddingcited by 12
  15. 2018Neural Machine Translation of Text from Non-Native Speakerscited by 10
  16. 2019Cross lingual transfer learning for zero-resource domain adaptationcited by 6
  17. 2019On Geometric Structure of Activation Spaces in Neural Networkscited by 4
  18. 2016Computing the Approximate Convex Hull in High Dimensionscited by 3

Built on by

Not cited yet.