# Key-Value Retrieval Networks for Task-Oriented Dialogue

## TL;DR

This paper introduces a neural dialogue system with a key-value retrieval mechanism that effectively manages multi-domain, knowledge-grounded conversations without explicit state modeling, demonstrated on a new in-car assistant dataset.

## Contribution

The work presents a novel end-to-end neural dialogue architecture that uses key-value retrieval for multi-domain knowledge integration, outperforming existing systems.

## Key findings

- Outperforms rule-based and neural baselines on the new dataset
- Effectively handles multi-domain, knowledge-grounded dialogues
- Achieves higher automatic and human evaluation scores

## Abstract

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.