A Reinforced Generation of Adversarial Samples for Neural Machine Translation

Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of these systems—fathoming how and when neural-based systems fail in such cases is critical for industrial maintenance. Instead of collecting and analyzing bad cases using limited handcrafted error features, here we investigate this issue by generating adversarial examples via a new paradigm based on reinforcement learning. Our paradigm could expose pitfalls for a given performance metric, e.g., BLEU, and could target any given neural machine translation architecture. We conduct experiments of adversarial attacks on two mainstream neural machine translation architectures, RNN-search, and Transformer. The results show that our method efficiently produces stable attacks with meaning-preserving adversarial examples. We also present a qualitative and quantitative analysis for the preference pattern of the attack, demonstrating its capability of pitfall exposure.

[1]  Haizhou Li,et al.  Named-Entity Tagging and Domain adaptation for Better Customized Translation , 2018, NEWS@ACL.

[2]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[3]  Zhiyuan Liu,et al.  Word-level Textual Adversarial Attacking as Combinatorial Optimization , 2019, ACL.

[4]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[5]  Yonatan Belinkov,et al.  Synthetic and Natural Noise Both Break Neural Machine Translation , 2017, ICLR.

[6]  Matt Post,et al.  A Call for Clarity in Reporting BLEU Scores , 2018, WMT.

[7]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[8]  Jinfeng Yi,et al.  Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples , 2018, AAAI.

[9]  Sergey Levine,et al.  High-Dimensional Continuous Control Using Generalized Advantage Estimation , 2015, ICLR.

[10]  Dejing Dou,et al.  On Adversarial Examples for Character-Level Neural Machine Translation , 2018, COLING.

[11]  Yang Liu,et al.  Towards Robust Neural Machine Translation , 2018, ACL.

[12]  Roman Neruda,et al.  Evolutionary generation of adversarial examples for deep and shallow machine learning models , 2016, MISNC, SI, DS 2016.

[13]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[14]  Graham Neubig,et al.  On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models , 2019, NAACL.

[15]  Lei Li,et al.  CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling , 2018, AAAI.

[16]  Yong Cheng,et al.  Robust Neural Machine Translation with Doubly Adversarial Inputs , 2019, ACL.

[17]  Jun Suzuki,et al.  Effective Adversarial Regularization for Neural Machine Translation , 2019, ACL.

[18]  Ashish Agarwal,et al.  Hallucinations in Neural Machine Translation , 2018 .

[19]  Sameer Singh,et al.  Generating Natural Adversarial Examples , 2017, ICLR.

[20]  J. Andrew Bagnell,et al.  Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy , 2010 .

[21]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[22]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[23]  Jiajun Zhang,et al.  Addressing Troublesome Words in Neural Machine Translation , 2018, EMNLP.

[24]  Mingyan Liu,et al.  Generating Adversarial Examples with Adversarial Networks , 2018, IJCAI.

[25]  Noam Shazeer,et al.  Adafactor: Adaptive Learning Rates with Sublinear Memory Cost , 2018, ICML.

[26]  Lijun Wu,et al.  A Study of Reinforcement Learning for Neural Machine Translation , 2018, EMNLP.

[27]  Omer Levy,et al.  Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation , 2019, EMNLP.

[28]  Akshay Chaturvedi,et al.  Exploring the Robustness of NMT Systems to Nonsensical Inputs , 2019 .

[29]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[30]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[31]  Joelle Pineau,et al.  An Actor-Critic Algorithm for Sequence Prediction , 2016, ICLR.