A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems
This work addresses the problem of generating more stable and readable responses in knowledge-based task-oriented dialogue systems, offering an incremental improvement over existing neural approaches.
The paper tackles the instability and poor readability of neural task-oriented dialogue systems by proposing a template-guided hybrid pointer network that retrieves relevant answers from a domain-specific repository to guide generation. It achieves significantly better performance than state-of-the-art methods across four datasets, as shown by improved automatic evaluation metrics.
Most existing neural network based task-oriented dialogue systems follow encoder-decoder 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 knowledge-based 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.