From Unsupervised Machine Translation To Adversarial Text Generation
This work addresses text generation for multilingual applications, but it is incremental as it builds on existing unsupervised translation and GAN methods.
The paper tackles the problem of generating fluent text in multiple languages by proposing B-GAN, a bilingual adversarial text generator that learns from an unsupervised neural machine translation system, resulting in more fluent sentences with half the parameters compared to monolingual baselines.
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.