SPM: 美团搜索中用于相关性建模的结构化预训练与匹配架构
SPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search
AI总结：
针对美团生活服务搜索中结构化文档字段分布差异大、重要性与长度不均导致的相关性建模难题，提出两阶段结构化预训练与匹配架构SPM，经实验验证有效提升性能且已上线部署。
摘要：
在电商搜索中，查询与文档的相关性是保障用户体验的核心要求。与提供商品的传统电商平台不同，用户在美团这类生活服务平台上搜索的主要是商品服务商，这类主体通常拥有丰富的结构化信息，例如名称、地址、类别、数千款商品等。利用这些丰富的结构化内容进行搜索相关性建模存在诸多挑战，原因如下：（1）结构化文档的不同字段之间存在语言分布差异，导致难以直接采用BERT等现成的预训练语言模型方法。（2）不同字段的重要性通常不同，且长度差异极大，难以提取对相关性匹配有帮助的文档信息。\n为解决这些问题，本文提出了一种新颖的两阶段预训练与匹配架构，用于处理含丰富结构化信息的文档的相关性匹配任务。在预训练阶段，我们提出了一种有效的预训练方法，同时以查询和文档的多个字段作为输入，其中包含针对长字段的有效信息压缩方法。在相关性匹配阶段，我们提出了一种新颖的匹配方法，利用搜索查询中的领域知识生成更有效的文档表示，用于相关性打分。在数百万用户上开展的大量离线实验与在线A/B测试验证了所提架构能有效提升相关性建模性能。该模型已上线部署，为美团搜索流量提供服务已超过一年。
英文摘要：
In e-commerce search, relevance between query and documents is an essential requirement for satisfying user experience. Different from traditional e-commerce platforms that offer products, users search on life service platforms such as Meituan mainly for product providers, which usually have abundant structured information, e.g. name, address, category, thousands of products. Modeling search relevance with these rich structured contents is challenging due to the following issues: (1) there is language distribution discrepancy among different fields of structured document, making it difficult to directly adopt off-the-shelf pretrained language model based methods like BERT. (2) different fields usually have different importance and their length vary greatly, making it difficult to extract document information helpful for relevance matching. To tackle these issues, in this paper we propose a novel two-stage pretraining and matching architecture for relevance matching with rich structured documents. At pretraining stage, we propose an effective pretraining method that employs both query and multiple fields of document as inputs, including an effective information compression method for lengthy fields. At relevance matching stage, a novel matching method is proposed by leveraging domain knowledge in search query to generate more effective document representations for relevance scoring. Extensive offline experiments and online A/B tests on millions of users verify that the proposed architectures effectively improve the performance of relevance modeling. The model has already been deployed online, serving the search traffic of Meituan for over a year.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
