How did we get here? Summarizing conversation dynamics

Yilun Hua, Nicholas Chernogor, Yuzhe Gu, Seoyeon Jeong, Miranda Luo, Cristian Danescu-Niculescu-Mizil


Abstract
Throughout a conversation, the way participants interact with each other is in constant flux: their tones may change, they may resort to different strategies to convey their points, or they might alter their interaction patterns. An understanding of these dynamics can complement that of the actual facts and opinions discussed, offering a more holistic view of the trajectory of the conversation: how it arrived at its current state and where it is likely heading.In this work, we introduce the task of summarizing the dynamics of conversations, by constructing a dataset of human-written summaries, and exploring several automated baselines. We evaluate whether such summaries can capture the trajectory of conversations via an established downstream task: forecasting whether an ongoing conversation will eventually derail into toxic behavior. We show that they help both humans and automated systems with this forecasting task. Humans make predictions three times faster, and with greater confidence, when reading the summaries than when reading the transcripts. Furthermore, automated forecasting systems are more accurate when constructing, and then predicting based on, summaries of conversation dynamics, compared to directly predicting on the transcripts.
Anthology ID:
2024.naacl-long.414
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7445–7470
Language:
URL:
https://aclanthology.org/2024.naacl-long.414
DOI:
Bibkey:
Cite (ACL):
Yilun Hua, Nicholas Chernogor, Yuzhe Gu, Seoyeon Jeong, Miranda Luo, and Cristian Danescu-Niculescu-Mizil. 2024. How did we get here? Summarizing conversation dynamics. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7445–7470, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
How did we get here? Summarizing conversation dynamics (Hua et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.414.pdf
Copyright:
 2024.naacl-long.414.copyright.pdf