Improvement in Machine Translation with Generative Adversarial Networks

by   Jay Ahn, et al.
Cal Poly

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.


page 1

page 2

page 3

page 4


Unsupervised Neural Machine Translation with Weight Sharing

Unsupervised neural machine translation (NMT) is a recently proposed app...

Adversarial Neural Machine Translation

In this paper, we study a new learning paradigm for Neural Machine Trans...

Implications of Multi-Word Expressions on English to Bharti Braille Machine Translation

In this paper, we have shown the improvement of English to Bharti Braill...

Bilingual-GAN: A Step Towards Parallel Text Generation

Latent space based GAN methods and attention based sequence to sequence ...

Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation

Subword segmenters like BPE operate as a preprocessing step in neural ma...

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

This paper proposes an approach for applying GANs to NMT. We build a con...

Using logical form encodings for unsupervised linguistic transformation: Theory and applications

We present a novel method to architect automatic linguistic transformati...

Please sign up or login with your details

Forgot password? Click here to reset