Conversation disentanglement with bi-level contrastive learning

• Main Authors: HUANG, Chengyu, ZHANG, Zheng, FEI, Hao, LIAO, Lizi
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Labeled data; Model-based OPC; Multi-party conversations; Public dataset; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/7585; https://ink.library.smu.edu.sg/context/sis_research/article/8588/viewcontent/2210.15265.pdf
• Institution: Singapore Management University

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.