With the rapid progress of deep neural models and the explosion of available data resources, dialogue systems that supports extensive topics and chit-chat conversations are emerging as a research hot-spot for many communities, e.g., information retrieval (IR), natural language processing (NLP), and machine learning (ML). Building a chit-chat system with retrieval techniques is an essential task and has achieved great success in the past few years. The advance of chit-chat systems, in turn, can support extensive IR tasks, e.g., conversational search and conversational recommendation. To facilitate the development of both retrieval-based chit-chat systems and IR tasks supported by these systems, we survey chit-chat systems from two perspectives: (1) techniques to build chit-chat systems, i.e., deep retrieval-based models, generative methods, and their ensembles, and (2) chit-chat components in completing IR tasks. In each aspect, we present cutting-edge neural methods and summarize the core challenges encountered and possible research directions.

随着深度神经模型的快速发展和可用数据资源的爆炸式增长，支持广泛主题和闲聊对话的对话系统正在成为许多社区的研究热点，例如信息检索（IR）、自然语言处理(NLP) 和机器学习 (ML)。使用检索技术构建聊天系统是一项必不可少的任务，并且在过去几年中取得了巨大成功。反过来，闲聊系统的进步可以支持广泛的 IR 任务，例如会话搜索和会话推荐。为了促进基于检索的聊天系统和这些系统支持的 IR 任务的开发，我们从两个角度调查聊天系统：（1）构建聊天系统的技术，即基于深度检索的模型，生成方法，及其合奏，以及 (2) 完成 IR 任务的闲聊组件。在每个方面，我们都介绍了前沿的神经方法，并总结了遇到的核心挑战和可能的研究方向。