Key-Value Retrieval Networks for Task-Oriented Dialogue
This addresses the challenge of grounding multi-domain discourse for in-car personal assistants, representing a novel method rather than an incremental improvement.
The authors tackled the problem of neural task-oriented dialogue systems struggling to interface with knowledge bases by proposing a new neural dialogue agent with a key-value retrieval mechanism, which significantly outperformed rule-based and other neural systems on a new dataset of 3,031 dialogues across three domains.
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base. In this work, we seek to address this problem by proposing a new neural dialogue agent that is able to effectively sustain grounded, multi-domain discourse through a novel key-value retrieval mechanism. The model is end-to-end differentiable and does not need to explicitly model dialogue state or belief trackers. We also release a new dataset of 3,031 dialogues that are grounded through underlying knowledge bases and span three distinct tasks in the in-car personal assistant space: calendar scheduling, weather information retrieval, and point-of-interest navigation. Our architecture is simultaneously trained on data from all domains and significantly outperforms a competitive rule-based system and other existing neural dialogue architectures on the provided domains according to both automatic and human evaluation metrics.