Key-Value Retrieval Networks for Task-Oriented Dialogue

WS 2017  ·  Mihail Eric, Christopher D. Manning ·

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. read more

PDF Abstract WS 2017 PDF WS 2017 Abstract

Datasets


Introduced in the Paper:

KVRET
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Task-Oriented Dialogue Systems KVRET KV Retrieval Net Entity F1 48.0 # 5
BLEU 13.2 # 4

Methods


No methods listed for this paper. Add relevant methods here