Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which usually initialize parameters by query reformulation to discover contextualized dependency, have trouble in understanding the dialogue structure information and struggle with contextual semantic vanishing. In this paper, we propose \fullmodel (\model) which is a new post-training paradigm with three self-supervised tasks to efficiently initialize the conversational search model to enhance the dialogue structure and contextual semantic understanding. Furthermore, the \model can be plugged into most of the existing conversational models to boost their performance. To verify the effectiveness of our proposed method, we apply the conversational encoder post-trained by \model on the conversational search task using two benchmark datasets: CAsT-19 and CAsT-20. Extensive experiments that our \model can boost the performance of several existing conversational search methods. Our source code is available at \url{https://github.com/morecry/SSP}.

翻译：对话搜索已被视为下一代搜索范式。受数据稀缺性限制，现有方法大多将训练完善的即席检索器蒸馏至对话检索器中。然而，这些通常通过查询改写初始化参数以发现上下文依赖关系的方法，难以理解对话结构信息，并面临上下文语义消失问题。本文提出\fullmodel (\model)——一种采用三项自监督任务的新型后训练范式，可高效初始化对话搜索模型，增强对话结构与上下文语义理解能力。此外，\model可被嵌入现有大多数对话模型以提升其性能。为验证该方法有效性，我们利用\model后训练的对话编码器，在两个基准数据集CAsT-19和CAsT-20上开展对话搜索任务实验。大量实验表明，\model能显著提升多种现有对话搜索方法的性能。我们的源代码已开源至\url{https://github.com/morecry/SSP}。