Abstract
Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose an adversarial latent space based model capable of generating parallel sentences in two languages concurrently and translating bidirectionally. The bilingual generation goal is achieved by sampling from the latent space that is shared between both languages. First two denoising autoencoders are trained, with shared encoders and back-translation to enforce a shared latent state between the two languages. The decoder is shared for the two translation directions. Next, a GAN is trained to generate synthetic "code" mimicking the languages' shared latent space. This code is then fed into the decoder to generate text in either language. We perform our experiments on Europarl and Multi30k datasets, on the English-French language pair, and document our performance using both supervised and unsupervised machine translation.
Abstract (translated)
基于潜在空间的gan方法和基于注意的序列对序列模型分别在文本生成和无监督机器翻译方面取得了令人印象深刻的效果。利用这两个领域,我们提出了一个基于对抗性潜在空间的模型,该模型能够同时生成两种语言的平行句,并进行双向翻译。双语生成的目标是通过从两种语言共享的潜在空间中取样来实现的。前两个去噪自动编码器经过训练,使用共享编码器和反向翻译来强制两种语言之间的共享潜在状态。解码器为两个翻译方向共享。接下来,一个gan被训练生成模拟语言共享潜在空间的合成“代码”。然后将此代码输入解码器以生成任何一种语言的文本。我们在Europarl和MULTI30K数据集、英法语言对上执行实验,并使用有监督和无监督的机器翻译记录我们的性能。
URL
https://arxiv.org/abs/1904.04742