PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation
Not on the map. Why?
Abstract (arXiv)
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 to be useful to alleviate this problem. Existing methods for adversarial example generation (AEG) are word-level or character-level, which ignore the ubiquitous phrase structure. In this paper, we propose a Phrase-level Adversarial Example Generation (PAEG) framework to enhance the robustness of the translation model. Our method further improves the gradient-based word-level AEG method by adopting a phrase-level substitution strategy. We verify our method on three benchmarks, including LDC Chinese-English, IWSLT14 German-English, and WMT14 English-German tasks. Experimental results demonstrate that our approach significantly improves translation performance and robustness to noise compared to previous strong baselines.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 55 references that are in the map. First posted on arXiv 6 Jan 2022.
Builds on
43 of 55 references.
References · 43
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2013Intriguing properties of neural networkscited by 5,114
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
- 2017Convolutional Sequence to Sequence Learningcited by 550
31 more
- 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
- 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
- 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
- 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
- 2016Professor Forcing: A New Algorithm for Training Recurrent Networkscited by 214
- 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
- 2016Dual Learning for Machine Translationcited by 146
- 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
- 2018Achieving Human Parity on Automatic Chinese to English News Translationcited by 119
- 2016Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanismcited by 117
- 2019Robust Neural Machine Translation with Doubly Adversarial Inputscited by 105
- 2017Adversarial Learning for Neural Dialogue Generationcited by 103
- 2018The Best of Both Worlds: Combining Recent Advances in Neural Machine Translationcited by 101
- 2015Multi-task Sequence to Sequence Learningcited by 94
- 2018On Adversarial Examples for Character-Level Neural Machine Translationcited by 85
- 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
- 2016Toward Multilingual Neural Machine Translation with Universal Encoder and Decodercited by 76
- 2018SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translationcited by 72
- 2020Balancing Training for Multilingual Neural Machine Translationcited by 71
- 2020AdvAug: Robust Adversarial Augmentation for Neural Machine Translationcited by 66
- 2019Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translationcited by 52
- 2020Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translationcited by 51
- 2019Improving Robustness of Machine Translation with Synthetic Noisecited by 36
- 2018Towards Robust Neural Machine Translationcited by 35
- 2020Neural Topic Modeling with Bidirectional Adversarial Trainingcited by 29
- 2020DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checkingcited by 26
- 2017Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Netscited by 20
- 2020NAT: Noise-Aware Training for Robust Neural Sequence Labelingcited by 17
- 2020Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentationcited by 6
- 2019Distilling Knowledge Learned in BERT for Text Generationcited by 5
- 2018Neural Phrase-to-Phrase Machine Translationcited by 4
Built on by
Citing papers per year: 2023: 2.
2 papers.