Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2022

Abstract

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance relations but pay inadequate attention to the utterance-to-context relation modeling. Second, a huge amount of human annotated data is required for training, which is expensive to obtain in practice. To address these issues, we propose a general disentangle model based on bi-level contrastive learning. It brings closer utterances in the same session while encourages each utterance to be near its clustered session prototypes in the representation space. Unlike existing approaches, our disentangle model works in both supervised settings with labeled data and unsupervised settings when no such data is available. The proposed method achieves new state-ofthe-art performance results on both settings across several public datasets.

Keywords

Labeled data, Model-based OPC, Multi-party conversations, Public dataset

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing EMNLP, Abu Dhabi, December 7-11

First Page

2985

Last Page

2996

Publisher

ACL

City or Country

Abu Dhabi

Copyright Owner and License

Authors

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Additional URL

https://aclanthology.org/2022.findings-emnlp.217/

Share

COinS