Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue BERT (DialBERT), which integrates local and global semantics in a single stream of messages to disentangle the conversations that mixed together. We employ BERT to capture the matching information in each utterance pair at the utterance-level, and use a BiLSTM to aggregate and incorporate the context-level information. With only a 3% increase in parameters, a 12% improvement has been attained in comparison to BERT, based on the F1-Score. The model achieves a state-of-the-art result on the a new dataset proposed by IBM and surpasses previous work by a substantial margin.
@article{arxiv.2004.03760,
title = {DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement},
author = {Tianda Li and Jia-Chen Gu and Xiaodan Zhu and Quan Liu and Zhen-Hua Ling and Zhiming Su and Si Wei},
journal= {arXiv preprint arXiv:2004.03760},
year = {2021}
}