Recent works have shown that generative data augmentation, where synthetic
samples generated from deep generative models complement the training dataset,
benefit NLP tasks. In this work, we extend this approach to the task of dialog
state tracking for goal-oriented dialogs. Due to the inherent hierarchical
structure of goal-oriented dialogs over utterances and related annotations, the
deep generative model must be capable of capturing the coherence among
different hierarchies and types of dialog features. We propose the Variational
Hierarchical Dialog Autoencoder (VHDA) for modeling the complete aspects of
goal-oriented dialogs, including linguistic features and underlying structured
annotations, namely speaker information, dialog acts, and goals. The proposed
architecture is designed to model each aspect of goal-oriented dialogs using
inter-connected latent variables and learns to generate coherent goal-oriented
dialogs from the latent spaces. To overcome training issues that arise from
training complex variational models, we propose appropriate training
strategies. Experiments on various dialog datasets show that our model improves
the downstream dialog trackers' robustness via generative data augmentation. We
also discover additional benefits of our unified approach to modeling
goal-oriented dialogs: dialog response generation and user simulation, where
our model outperforms previous strong baselines.

本文提出了一种名为 Variational Hierarchical Dialog Autoencoder（VHDA）的深度生成模型，用于 goal-oriented dialogs 的任务，它有效地捕获了不同层次和类型的 dialog features 之间的一致性，并且使用生成性数据增强方案，提高了下游目标跟踪器的鲁棒性，同时也在 dialog response generation 和 user simulation 方面具有良好表现。