Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of pre-trained language models when labeled data is insufficient. However, it remains challenging to incorporate ST into attribute-controllable language generation. Augmented by only self-generated pseudo text, generation models over-emphasize exploitation of the previously learned space, suffering from a constrained generalization boundary. We revisit ST and propose a novel method, DuNST to alleviate this problem. DuNST jointly models text generation and classification with a shared Variational AutoEncoder and corrupts the generated pseudo text by two kinds of flexible noise to disturb the space. In this way, our model could construct and utilize both pseudo text from given labels and pseudo labels from available unlabeled text, which are gradually refined during the ST process. We theoretically demonstrate that DuNST can be regarded as enhancing exploration towards the potential real text space, providing a guarantee of improved performance. Experiments on three controllable generation tasks show that DuNST could significantly boost control accuracy while maintaining comparable generation fluency and diversity against several strong baselines.

翻译：自训练方法通过在标注数据不足时增强预训练语言模型的微调过程，已在语言理解领域重新兴起。然而，将自训练方法融入属性可控语言生成仍具挑战性。仅依赖自生成的伪文本进行增强，生成模型会过度利用先前习得的空间，导致泛化边界受限。本文重新审视自训练方法，提出一种新型方法DuNST以缓解该问题。DuNST通过共享变分自编码器联合建模文本生成与分类，并利用两种灵活噪声扰动生成的伪文本空间。由此，我们的模型能够构建并利用来自给定标签的伪文本和来自未标注文本的伪标签，这些数据在自训练过程中逐步优化。理论分析表明，DuNST可视为增强对潜在真实文本空间的探索，从而保证性能提升。在三个可控生成任务上的实验显示，与多个强基线相比，DuNST能在保持可比生成流畅性和多样性的同时，显著提升控制准确率。