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, 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 setting with labeled data and unsupervised setting when no such data is available. The proposed method achieves new state-of-the-art performance on both settings across several public datasets.- Anthology ID:
- 2022.findings-emnlp.217
- 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:
- 2985–2996
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.217
- DOI:
- 10.18653/v1/2022.findings-emnlp.217
- Cite (ACL):
- Chengyu Huang, Zheng Zhang, Hao Fei, and Lizi Liao. 2022. Conversation Disentanglement with Bi-Level Contrastive Learning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2985–2996, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Conversation Disentanglement with Bi-Level Contrastive Learning (Huang et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.findings-emnlp.217.pdf