E-commerce sponsored search contributes an important part of revenue for the e-commerce company. In consideration of effectiveness and efficiency, a large-scale sponsored search system commonly adopts a multi-stage architecture. We name these stages as \textit{ad retrieval}, \textit{ad pre-ranking} and \textit{ad ranking}. \textit{Ad retrieval} and \textit{ad pre-ranking} are collectively referred to as \textit{ad matching} in this paper. We propose an end-to-end neural matching framework (EENMF) to model two tasks---\textit{vector-based ad retrieval} and \textit{neural networks based ad pre-ranking}. Under the deep \textit{matching} framework, \textit{vector-based ad retrieval} harnesses user recent behavior sequence to retrieve relevant ad candidates without the constraint of keyword bidding. Simultaneously, the deep model is employed to perform the global pre-ranking of ad candidates from multiple retrieval paths effectively and efficiently. Besides, the proposed model tries to optimize the pointwise cross-entropy loss which is consistent with the objective of predict models in the ranking stage. We conduct extensive evaluation to validate the performance of the proposed framework. In the real traffic of a large-scale e-commerce sponsored search, the proposed approach significantly outperforms the baseline.

本研究提出了一种端到端的神经匹配框架 (EENMF)，用于模拟基于向量的广告检索和基于神经网络的广告预排名。在大规模赞助搜索中，所提出的方法显著优于基准测试。

EENMF: 一种面向电子商务赞助搜索的端到端神经匹配框架