Key-Value Retrieval Networks for Task-Oriented Dialogue

Mihail Eric, Lakshmi Krishnan, Francois Charette, Christopher D. Manning


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.
Anthology ID:
W17-5506
Volume:
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue
Month:
August
Year:
2017
Address:
Saarbrücken, Germany
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
37–49
Language:
URL:
https://aclanthology.org/W17-5506
DOI:
10.18653/v1/W17-5506
Bibkey:
Cite (ACL):
Mihail Eric, Lakshmi Krishnan, Francois Charette, and Christopher D. Manning. 2017. Key-Value Retrieval Networks for Task-Oriented Dialogue. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 37–49, Saarbrücken, Germany. Association for Computational Linguistics.
Cite (Informal):
Key-Value Retrieval Networks for Task-Oriented Dialogue (Eric et al., SIGDIAL 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5506.pdf
Code
 additional community code