Conversation Disentanglement with Bi-Level Contrastive Learning
This improves multi-party conversation processing for applications like chatbots or social media analysis, though it appears incremental as it builds on existing disentanglement methods.
The paper tackles conversation disentanglement by proposing a bi-level contrastive learning model that addresses overemphasis on pairwise utterance relations and high annotation costs, achieving state-of-the-art performance in both supervised and unsupervised settings across multiple public datasets.
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.