Improvement in Machine Translation with Generative Adversarial Networks

2021/11/30 by Jay Ahn, Ahn, Jay, Hari Madhu +4
Computer Science · Engineering · #Adversarial system #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Deep learning #Engineering #FOS: Computer and information sciences #Fluent #Generative adversarial network #Generative grammar #Generator (circuit theory) #Machine translation #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Natural language processing #Phrase #Sentence #Simulation #Topic Modeling #Transformer #Translation (biology) #cs.CL

paper · pdf · doi:10.48550/arxiv.2111.15166

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/11/30 · openalex publication_date 2021/11/30 · arxiv updated 2021/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. We take inspiration from RelGAN, a model for text generation, and NMT-GAN, an adversarial machine translation model, to implement a model that learns to transform awkward, non-fluent English sentences to fluent ones, while only being trained on monolingual corpora. We utilize a parameter λ to control the amount of deviation from the input sentence, i.e. a trade-off between keeping the original tokens and modifying it to be more fluent. Our results improved upon phrase-based machine translation in some cases. Especially, GAN with a transformer generator shows some promising results. We suggests some directions for future works to build upon this proof-of-concept.

Citations

• Generative Adversarial Networks
• Conditional Generative Adversarial Nets
• Categorical Reparameterization with Gumbel-Softmax
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• Toward Controlled Generation of Text
• Long Text Generation via Adversarial Training with Leaked Information
• Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study

Related

• Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
• Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation
• High-Quality Data Augmentation for Low-Resource NMT: Combining a Translation Memory, a GAN Generator, and Filtering
• Adversarial Neural Machine Translation
• From Unsupervised Machine Translation To Adversarial Text Generation