Toward Controlled Generation of Text
This addresses the challenge of controlled text generation for natural language processing applications, representing an incremental advance over existing methods.
The paper tackled the problem of generating natural language sentences with dynamically controlled attributes by learning disentangled latent representations, achieving realistic sentence generation with validated accuracy in quantitative evaluation.
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynamically controlled by learning disentangled latent representations with designated semantics. We propose a new neural generative model which combines variational auto-encoders and holistic attribute discriminators for effective imposition of semantic structures. With differentiable approximation to discrete text samples, explicit constraints on independent attribute controls, and efficient collaborative learning of generator and discriminators, our model learns highly interpretable representations from even only word annotations, and produces realistic sentences with desired attributes. Quantitative evaluation validates the accuracy of sentence and attribute generation.