论文标题
Dialbert：一种用于对话解散的层次预培训模型
DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
论文作者
论文摘要
解开是一个同时在同一频道中进行多次对话的问题，听众应决定哪种话语是他将要回应的对话的一部分。我们提出了一个名为对话Bert（Dialbert）的新模型，该模型将本地语义和全局语义集成在单个消息流中，以解开混合在一起的对话。我们采用BERT在话语级别的每个话语对中捕获匹配信息，并使用Bilstm来汇总和合并上下文级别的信息。与BERT相比，基于F1得分，参数仅增加了3％，因此获得了12％的提高。该模型在IBM提出的新数据集上实现了最新的结果，并超过了先前的工作。
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.
