论文标题
用两相自我实践进行自我训练，以创造几次对话
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
论文作者
论文摘要
在以任务为导向的对话系统中，由于含义表示（MRS）的响应产生通常会受到培训示例有限，因为对MR到文本对的高成本成本很高。以前的自我训练的作品利用微调的对话模型自动生成伪标记的MR到文本对，以进行进一步的微调。但是，某些自我提高的数据可能是嘈杂的或不明智的，对于该模型可以学习。在这项工作中，我们提出了一个两阶段的自我实践程序，以产生高质量的伪标记的MR到文本对：第一阶段根据模型的预测不确定性选择了最有用的MRS；使用选定的MRS，第二阶段通过从每个MR中汇总多个扰动潜在表示，从而产生准确的响应。在两个基准数据集（几乎没有Shotwoz）和几个ShotsGD上进行的经验实验表明，我们的方法通常在自动和人类评估上都优于现有的自我训练方法。
In task-oriented dialogue systems, response generation from meaning representations (MRs) often suffers from limited training examples, due to the high cost of annotating MR-to-Text pairs. Previous works on self-training leverage fine-tuned conversational models to automatically generate pseudo-labeled MR-to-Text pairs for further fine-tuning. However, some self-augmented data may be noisy or uninformative for the model to learn from. In this work, we propose a two-phase self-augmentation procedure to generate high-quality pseudo-labeled MR-to-Text pairs: the first phase selects the most informative MRs based on model's prediction uncertainty; with the selected MRs, the second phase generates accurate responses by aggregating multiple perturbed latent representations from each MR. Empirical experiments on two benchmark datasets, FewShotWOZ and FewShotSGD, show that our method generally outperforms existing self-training methods on both automatic and human evaluations.
