ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification

Marco Casadio; Luca Arnaboldi; Matthew Daggitt; Omri Isac; Tanvi Dinkar; Daniel Kienitz; Verena Rieser; Ekaterina Komendantskaya

doi:10.29007/7wxb

ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification

12 pages•Published: October 23, 2023

Marco Casadio, Luca Arnaboldi, Matthew Daggitt, Omri Isac, Tanvi Dinkar, Daniel Kienitz, Verena Rieser and Ekaterina Komendantskaya

Abstract

Verification of machine learning models used in Natural Language Processing (NLP) is known to be a hard problem. In particular, many known neural network verification methods that work for computer vision and other numeric datasets do not work for NLP. Here, we study technical reasons that underlie this problem. Based on this analysis, we propose practical methods and heuristics for preparing NLP datasets and models in a way that renders them amenable to state-of-the-art verification methods. We implement these methods as a Python library called ANTONIO that links to the neural network verifiers ERAN and Marabou. We perform evaluation of the tool using an NLP dataset R-U-A-Robot suggested as a benchmark for verifying legally critical NLP applications. We hope that, thanks to its general applicability, this work will open novel possibilities for including NLP verification problems into neural network verification competitions, and will popularise NLP problems within this community.

Keyphrases: abstract interpretation, adversarial training, Neural Network Verification, NLP

In: Nina Narodytska, Guy Amir, Guy Katz and Omri Isac (editors). Proceedings of the 6th Workshop on Formal Methods for ML-Enabled Autonomous Systems, vol 16, pages 59--70

Links:	https://easychair.org/publications/paper/9ZGS
	https://doi.org/10.29007/7wxb

BibTeX entry

@inproceedings{FoMLAS2023:ANTONIO_Towards_Systematic_Method,
  author    = {Marco Casadio and Luca Arnaboldi and Matthew Daggitt and Omri Isac and Tanvi Dinkar and Daniel Kienitz and Verena Rieser and Ekaterina Komendantskaya},
  title     = {ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification},
  booktitle = {Proceedings of the 6th Workshop on Formal Methods for ML-Enabled Autonomous Systems},
  editor    = {Nina Narodytska and Guy Amir and Guy Katz and Omri Isac},
  series    = {Kalpa Publications in Computing},
  volume    = {16},
  pages     = {59--70},
  year      = {2023},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2515-1762},
  url       = {https://easychair.org/publications/paper/9ZGS},
  doi       = {10.29007/7wxb}}

Download PDF Open PDF in browser