A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems
Dingmin Wang, Ziyao Chen, Wanwei He, Zhong Li, Yunzhe Tao, Min Yang · 2021
Most existing neural network based taskoriented dialogue systems follow encoderdecoder paradigm, where the decoder purely depends on the source texts to generate a sequence of words, usually suffering from instability and poor readability.Inspired by the traditional template-based generation approaches, we propose a template-guided hybrid pointer network for the knowledgebased task-oriented dialogue system, which retrieves several potentially relevant answers from a pre-constructed domain-specific conversational repository as guidance answers, and incorporates the guidance answers into both the encoding and decoding processes.Specifically, we design a memory pointer network model with a gating mechanism to fully exploit the semantic correlation between the retrieved answers and the ground-truth response.We evaluate our model on four widely used task-oriented datasets, including one simulated and three manually created datasets.The experimental results demonstrate that the proposed model achieves significantly better performance than the state-of-the-art methods over different automatic evaluation metrics 1 .