论文标题
从无监督的机器翻译到对抗文本生成
From Unsupervised Machine Translation To Adversarial Text Generation
论文作者
论文摘要
我们提出了一个基于自我注意力的双语对抗文本生成器（B-GAN），可以学会从无监督的神经机器翻译系统的编码器表示中生成文本。 B-GAN能够生成分布式的潜在空间表示，该表示可以与基于注意的解码器配对以产生流利的句子。当对两种语言之间共享的编码器进行培训并与适当的解码器配对时，它可以用两种语言生成句子。 B-GAN使用自动编码器的重建损失的组合，翻译的跨域损失以及文本生成的基于GAN的对抗性损失。我们证明，B-GAN仅使用多种损失进行单语内团培训，与单语基线相比，在有效使用一半的参数数量的同时，会产生更多流利的句子。
We present a self-attention based bilingual adversarial text generator (B-GAN) which can learn to generate text from the encoder representation of an unsupervised neural machine translation system. B-GAN is able to generate a distributed latent space representation which can be paired with an attention based decoder to generate fluent sentences. When trained on an encoder shared between two languages and paired with the appropriate decoder, it can generate sentences in either language. B-GAN is trained using a combination of reconstruction loss for auto-encoder, a cross domain loss for translation and a GAN based adversarial loss for text generation. We demonstrate that B-GAN, trained on monolingual corpora only using multiple losses, generates more fluent sentences compared to monolingual baselines while effectively using half the number of parameters.
