paper-with-me

홈 › Papers

A Reinforced Generation of Adversarial Examples for Neural Machine Translation

2019-11-09 · ACL 2020 6 · Wei Zou, Shu-Jian Huang, Jun Xie, Xin-yu Dai, Jia-Jun Chen

Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this 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.

📄 PDF Abstract BibTeX arXiv:1911.03677

Code (1)

vergilus/NJUNMT-pytorch/tree/master/adversarials pytorch

Tasks

Machine TranslationReinforcement LearningTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

2023-07-24 · Neel Bhandari, Pin-Yu Chen

Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain conside…

Machine TranslationTranslation

Robust Neural Machine Translation with Doubly Adversarial Inputs

2019-06-06 · ACL 2019 7 · Yong Cheng, Lu Jiang, Wolfgang Macherey

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the tra…

Machine TranslationNMTTranslation

Crafting Adversarial Examples for Neural Machine Translation

2021-08-01 · ACL 2021 5 · Xinze Zhang, Junzhe Zhang, Zhenhua Chen, Kun He

Effective adversary generation for neural machine translation (NMT) is a crucial prerequisite for building robust machine translation systems. In this work, we investigate veritable evaluations of NMT adversarial attacks…

Machine TranslationNMTTranslationvalid

PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation

2022-01-06 · COLING 2022 10 · Juncheng Wan, Jian Yang, Shuming Ma, Dongdong Zhang 외

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved t…

Machine TranslationNMTTranslation

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

2017-03-15 · NAACL 2018 6 · Zhen Yang, Wei Chen, Feng Wang, Bo Xu

This paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. The generator aims to g…

Machine TranslationNMTSentenceTranslation