Dialogue disentanglement aims to group utterances in a long and multi-participant dialogue into threads. This is useful for discourse analysis and downstream applications such as dialogue response selection, where it can be the first step to construct a clean context/response set. Unfortunately, labeling all~\emph{reply-to} links takes quadratic effort w.r.t the number of utterances: an annotator must check all preceding utterances to identify the one to which the current utterance is a reply. In this paper, we are the first to propose a~\textbf{zero-shot} dialogue disentanglement solution. Firstly, we train a model on a multi-participant response selection dataset harvested from the web which is not annotated; we then apply the trained model to perform zero-shot dialogue disentanglement. Without any labeled data, our model can achieve a cluster F1 score of 25. We also fine-tune the model using various amounts of labeled data. Experiments show that with only 10\% of the data, we achieve nearly the same performance of using the full dataset\footnote{Code is released at \url{https://github.com/chijames/zero_shot_dialogue_disentanglement}}.

翻译：对话解纠缠旨在将长篇幅多参与方对话中的话语分组为线程。这对于话语分析及下游应用（如对话响应选择）具有重要意义，可成为构建干净上下文/响应集的首要步骤。然而，标注所有~reply-to~链接需要与话语数量呈二次增长的工作量：标注者必须检查所有先前话语，以确定当前话语所回复的对象。本文首次提出一种~\textbf{零样本}对话解纠缠方案。首先，我们在从网络获取的未标注多参与方响应选择数据集上训练模型；随后将训练完成的模型应用于零样本对话解纠缠。无需任何标注数据，我们的模型即可达到25的聚类F1分数。我们还使用不同量的标注数据对模型进行微调。实验表明，仅使用10\%的数据即可获得接近完整数据集的效果\footnote{代码已发布于 \url{https://github.com/chijames/zero_shot_dialogue_disentanglement}}。