Matching is a key problem in both search and recommendation, which is to measure the relevance of a document to a query or the interest of a user to an item. Machine learning has been exploited to address the problem, which learns a matching function based on input representations and from labeled data, also referred to as “learning to match”. In recent years, efforts have been made to develop deep learning techniques for matching tasks in search and recommendation. With the availability of a large amount of data, powerful computational resources, and advanced deep learning techniques, deep learning for matching now becomes the state-of-the-art technology for search and recommendation. The key to the success of the deep learning approach is its strong ability in learning of representations and generalization of matching patterns from data (e.g., queries, documents, users, items, and contexts, particularly in their raw forms).

This survey gives a systematic and comprehensive introduction to the deep matching models for search and recommendation developed recently. It first gives a unified view of matching in search and recommendation. In this way, the solutions from the two fields can be compared under one framework. Then, the survey categorizes the current deep learning solutions into two types: methods of representation learning and methods of matching function learning. The fundamental problems, as well as the state-of-the-art solutions of query-document matching in search and user-item matching in recommendation, are described. The survey aims to help researchers from both search and recommendation communities to get in-depth understanding and insight into the spaces, stimulate more ideas and discussions, and promote developments of new technologies.

Matching is not limited to search and recommendation. Similar problems can be found in paraphrasing, question answering, image annotation, and many other applications. In general, the technologies introduced in the survey can be generalized into a more general task of matching between objects from two spaces.

匹配是搜索和推荐中的关键问题，即测量文档与查询的相关性或用户对项目的兴趣。已经利用机器学习来解决该问题，该问题基于输入表示和标记的数据来学习匹配功能，也称为“学习匹配”。近年来，已经努力开发用于匹配搜索和推荐任务的深度学习技术。随着大量数据的可用性，强大的计算资源和先进的深度学习技术，用于匹配的深度学习现在已成为搜索和推荐的最新技术。深度学习方法成功的关键在于其强大的能力，可以学习表示形式并从数据中概括匹配模式（例如，

该调查对最近开发的搜索和推荐深层匹配模型进行了系统，全面的介绍。首先，它给出了搜索和推荐中匹配的统一视图。这样，可以在一个框架下比较两个领域的解决方案。然后，调查将当前的深度学习解决方案分为两种类型：表示学习方法和匹配函数学习方法。描述了基本问题以及搜索中的查询文档匹配和推荐中的用户项目匹配的最新解决方案。这项调查旨在帮助来自搜索和推荐社区的研究人员深入了解和洞察空间，激发更多想法和讨论，并促进新技术的发展。

匹配不仅限于搜索和推荐。类似的问题可以在释义，问题回答，图像注释和许多其他应用程序中找到。通常，可以将调查中引入的技术概括为在两个空间中的对象之间进行匹配的更一般的任务。