Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner

Yury Zemlyanskiy, Fei Sha


Abstract
There have been several attempts to define a plausible motivation for a chit-chat dialogue agent that can lead to engaging conversations. In this work, we explore a new direction where the agent specifically focuses on discovering information about its interlocutor. We formalize this approach by defining a quantitative metric. We propose an algorithm for the agent to maximize it. We validate the idea with human evaluation where our system outperforms various baselines. We demonstrate that the metric indeed correlates with the human judgments of engagingness.
Anthology ID:
K18-1053
Volume:
Proceedings of the 22nd Conference on Computational Natural Language Learning
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Anna Korhonen, Ivan Titov
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
551–561
Language:
URL:
https://aclanthology.org/K18-1053
DOI:
10.18653/v1/K18-1053
Bibkey:
Cite (ACL):
Yury Zemlyanskiy and Fei Sha. 2018. Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 551–561, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner (Zemlyanskiy & Sha, CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-1053.pdf
Data
DailyDialog