Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

Pengshan Cai, Hui Wan, Fei Liu, Mo Yu, Hong Yu, Sachindra Joshi


Abstract
We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information acquisition-oriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users.
Anthology ID:
2022.naacl-main.352
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4781–4796
Language:
URL:
https://aclanthology.org/2022.naacl-main.352
DOI:
10.18653/v1/2022.naacl-main.352
Bibkey:
Cite (ACL):
Pengshan Cai, Hui Wan, Fei Liu, Mo Yu, Hong Yu, and Sachindra Joshi. 2022. Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4781–4796, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition (Cai et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.352.pdf
Video:
 https://aclanthology.org/2022.naacl-main.352.mp4
Code
 ibm/reinforced-dialog-system-for-learning
Data
Wizard of Wikipedia