Unsupervised Learning of Hierarchical Conversation Structure

Bo-Ru Lu, Yushi Hu, Hao Cheng, Noah A. Smith, Mari Ostendorf


Abstract
Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This work introduces an unsupervised approach to learning hierarchical conversation structure, including turn and sub-dialogue segment labels, corresponding roughly to dialogue acts and sub-tasks, respectively. The decoded structure is shown to be useful in enhancing neural models of language for three conversation-level understanding tasks. Further, the learned finite-state sub-dialogue network is made interpretable through automatic summarization.
Anthology ID:
2022.findings-emnlp.415
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5657–5670
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.415
DOI:
10.18653/v1/2022.findings-emnlp.415
Bibkey:
Cite (ACL):
Bo-Ru Lu, Yushi Hu, Hao Cheng, Noah A. Smith, and Mari Ostendorf. 2022. Unsupervised Learning of Hierarchical Conversation Structure. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5657–5670, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Learning of Hierarchical Conversation Structure (Lu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.415.pdf