Structural Characterization for Dialogue Disentanglement

Xinbei Ma, Zhuosheng Zhang, Hai Zhao


Abstract
Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history for both human and machine. Previous studies mainly focus on utterance encoding methods with carefully designed features but pay inadequate attention to characteristic features of the structure of dialogues. We specially take structure factors into account and design a novel model for dialogue disentangling. Based on the fact that dialogues are constructed on successive participation and interactions between speakers, we model structural information of dialogues in two aspects: 1)speaker property that indicates whom a message is from, and 2) reference dependency that shows whom a message may refer to. The proposed method achieves new state-of-the-art on the Ubuntu IRC benchmark dataset and contributes to dialogue-related comprehension.
Anthology ID:
2022.acl-long.23
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
285–297
Language:
URL:
https://aclanthology.org/2022.acl-long.23
DOI:
10.18653/v1/2022.acl-long.23
Bibkey:
Cite (ACL):
Xinbei Ma, Zhuosheng Zhang, and Hai Zhao. 2022. Structural Characterization for Dialogue Disentanglement. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 285–297, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Structural Characterization for Dialogue Disentanglement (Ma et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.23.pdf
Software:
 2022.acl-long.23.software.zip
Code
 xbmxb/structurecharacterization4dd
Data
MolweniUbuntu IRC