Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure

Lu Ji, Lei Chen, Jing Li, Zhongyu Wei, Qi Zhang, Xuanjing Huang


Abstract
Vast amount of online conversations are produced on a daily basis, resulting in a pressing need to automatic conversation understanding. As a basis to structure a discussion, we identify the responding relations in the conversation discourse, which link response utterances to their initiations. To figure out who responded to whom, here we explore how the consistency of topic contents and dependency of discourse roles indicate such interactions, whereas most prior work ignore the effects of latent factors underlying word occurrences. We propose a neural model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links via exploiting topic consistency and discourse dependency. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts.
Anthology ID:
2024.sighan-1.7
Volume:
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Kam-Fai Wong, Min Zhang, Ruifeng Xu, Jing Li, Zhongyu Wei, Lin Gui, Bin Liang, Runcong Zhao
Venues:
SIGHAN | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–68
Language:
URL:
https://aclanthology.org/2024.sighan-1.7
DOI:
Bibkey:
Cite (ACL):
Lu Ji, Lei Chen, Jing Li, Zhongyu Wei, Qi Zhang, and Xuanjing Huang. 2024. Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure. In Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10), pages 58–68, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure (Ji et al., SIGHAN-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sighan-1.7.pdf