English

Extend Adversarial Policy Against Neural Machine Translation via Unknown Token

Computation and Language 2025-01-22 v1

Abstract

Generating adversarial examples contributes to mainstream neural machine translation~(NMT) robustness. However, popular adversarial policies are apt for fixed tokenization, hindering its efficacy for common character perturbations involving versatile tokenization. Based on existing adversarial generation via reinforcement learning~(RL), we propose the `DexChar policy' that introduces character perturbations for the existing mainstream adversarial policy based on token substitution. Furthermore, we improve the self-supervised matching that provides feedback in RL to cater to the semantic constraints required during training adversaries. Experiments show that our method is compatible with the scenario where baseline adversaries fail, and can generate high-efficiency adversarial examples for analysis and optimization of the system.

Keywords

Cite

@article{arxiv.2501.12183,
  title  = {Extend Adversarial Policy Against Neural Machine Translation via Unknown Token},
  author = {Wei Zou and Shujian Huang and Jiajun Chen},
  journal= {arXiv preprint arXiv:2501.12183},
  year   = {2025}
}

Comments

accepted by CCMT 2024()

R2 v1 2026-06-28T21:12:30.295Z