Adversarial Neural Machine Translation

By Lijun Wu, Yingce Xia, Li Zhao, Fei Tian, Tao Qin, J. Lai, Tie-Yan Liu. 2017

137 citations recorded by the source corpus.

In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success of generative adversarial networks (GANs), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elaborately designed Convolutional Neural Network (CNN). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English$\rightarrow$French and German$\rightarrow$English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Microsoft Research Asia’s Systems for WMT19 (2019, methodology): “Furthermore, some other techniques such as de-liberation learning (Xia et al., 2017b), adversarial learning (Wu et al., 2018b), and reinforcement learning (He et al., 2017; Wu et al., 2018a) could also hep and are worthy of exploration.”
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning (2018, methodology): “Similar to approaches for generative adversarial NMT (Yu et al., 2017; Wu et al., 2017) we prefer a simpler convolutional architecture based on word embeddings for the human reward estimation.”
Quark: Controllable Text Generation with Reinforced Unlearning (2022, background): “Recent works have explored applying RL on tasks such as question-answering [85, 86, 48, 84, 85], summarization [59, 54, 71, 61, 17, 52], and machine translation [59, 88, 80, 83, 82, 13, 67, 5, 50].”
CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training (2017, background): “GANs have shown tremendous success in generating samples from distributions such as image and video [37] and have even been proposed for language translation [38].”
Negative Training for Neural Dialogue Response Generation (2019, methodology): “We use the log derivative trick (Wu et al., 2017) for the gradient derivation of the generator: where x is one input data sample.”
On the Weaknesses of Reinforcement Learning for Neural Machine Translation (2019, background): “For some recent work on RL for NMT, see (Zhang et al., 2016; Li et al., 2017; Wu et al., 2017; Yu et al., 2017; Yang et al., 2018).”
TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks (2019, background): “GANs have been exploited recently in various NLP applications such as machine translation [24,25], dialogue models [15], question answering [26], and natural language generation [7,20,19,13,28,29].”
Language Generation with Recurrent Generative Adversarial Networks without Pre-training (2017, background): “Consequently, past work on using GANs for text generation has been based on pre-training (Yu et al., 2016; Li et al., 2017; Yang et al., 2017; Wu et al., 2017; Liang et al., 2017; Zhang et al., 2016; Shetty et al., 2017)”
Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation (2018, methodology): “However, due to the nondifferentiable of sequence-level objectives, previous works on sequence-level training (Ranzato et al., 2015; Shen et al., 2016; Bahdanau et al., 2016; Wu et al., 2016; He et al., 2016; Wu et al., 2017; Yang et al., 2017) mainly rely on reinforcement learning algorithms (Willi”
Neural Models of Text Normalization for Speech Applications (2019, background): “2014; Goodfellow 2016), which have achieved impressive results in vision-related tasks but which have been also applied to NLP tasks including machine translation (Wu et al. 2017; Yang et al. 2018).”
VIBE: Video Inference for Human Body Pose and Shape Estimation (2019, background): “Recent works have incorporated GANs into recurrent architectures to model sequence-to-sequence tasks like machine translation [54, 62, 63].”
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction (2018, unknown): “Wu et al. (2017) used a CNN over the 2D source-target representation as in our work, but only as a discriminator in an adversarial training setup.”
A Study of Reinforcement Learning for Neural Machine Translation (2018, methodology): “The last important strategy we would like to mention is the combination of MLE training objective with RL objective, which is assumed to further stabilize RL training process (Wu et al., 2016; Li et al., 2017; Wu et al., 2017a).”
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (2018, background): “Neural machine translation (NMT) has attracted much research attention in recent years (Bah-danau et al., 2014; Shen et al., 2018; Song et al., 2018; Xia et al., 2018; He et al., 2016; Wu et al., 2017, 2018).”
Sometimes We Want Ungrammatical Translations (2021, background): “Towards averting such scenarios, efforts along the lines of building robust models with adversarial training have been a common topic of study in natural language processing (Rajeswar et al., 2017; Wu et al., 2018).”
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (2017, background): “There are some differences in training strategies and experimental settings between (Wu et al., 2017) and this work.”
Neural Machine Translation with Adequacy-Oriented Learning (2018, unknown): “For example, the ﬁrst two problems are tackled by sequence level training using the REINFORCE algorithm (Ranzato et al. 2016; Bahdanau et al. 2017), minimum risk training (Shen et al. 2016), beam search optimization (Wiseman and Rush 2016) or adversarial learning (Wu et al. 2017; Yang et al. 2018).”
AgreeSum: Agreement-Oriented Multi-Document Summarization (2021, methodology): “, 2014) objectives, which have achieved good performance in some conditional generation tasks like textual style transfer and machine translation (Shen et al., 2017; Wu et al., 2018; Pang and Gimpel, 2019).”