Augmenting end-to-end dialogue systems with commonsense knowledge

Young, Tom, Cambria, Erik, Chaturvedi, Iti, Zhou, Hao, Biswas, Subham, and Huang, Minlie (2018) Augmenting end-to-end dialogue systems with commonsense knowledge. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. pp. 4970-4977. From: AAAI-18: 32nd AAAI Conference on Artificial Intelligence, 2-7 February 2018, New Orleans, LA, USA.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website:


Building dialogue systems that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human utterances in an interesting and engaging way, commonsense knowledge has to be integrated into the model effectively. In this paper, we investigate the impact of providing commonsense knowledge about the concepts covered in the dialogue. Our model represents the first attempt to integrating a large commonsense knowledge base into end-to-end conversational models. In the retrieval-based scenario, we propose a model to jointly take into account message content and related commonsense for selecting an appropriate response. Our experiments suggest that the knowledge-augmented models are superior to their knowledge-free counterparts.

Item ID: 63346
Item Type: Conference Item (Research - E1)
ISBN: 978-1-57735-800-8
Related URLs:
Copyright Information: Copyright © 2018, Association for the Advancement of Artificial Intelligence ( All rights reserved.
Date Deposited: 21 Jul 2020 00:13
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460208 Natural language processing @ 50%
46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461103 Deep learning @ 50%
SEO Codes: 90 COMMERCIAL SERVICES AND TOURISM > 9003 Tourism > 900302 Socio-Cultural Issues in Tourism @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page