Hierarchical neural networks are often used to model inherent structures within dialogues. For goal-oriented dialogues, these models miss a mechanism adhering to the goals and neglect the distinct conversational patterns between two interlocutors. In this work, we propose Goal-Embedded Dual Hierarchical Attentional Encoder-Decoder (G-DuHA) able to center around goals and capture interlocutor-level disparity while modeling goal-oriented dialogues. Experiments on dialogue generation, response generation, and human evaluations demonstrate that the proposed model successfully generates higher-quality, more diverse and goal-centric dialogues. Moreover, we apply data augmentation via goal-oriented dialogue generation for task-oriented dialog systems with better performance achieved.
@article{arxiv.1909.09220,
title = {Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation},
author = {Yi-An Lai and Arshit Gupta and Yi Zhang},
journal= {arXiv preprint arXiv:1909.09220},
year = {2019}
}