Uni-Match: A Semantic Unified Model for Query-Product Retrieval

Zhenyang Zhu, Rui-Jie Zhu, Yunrui Ge, Qihang Zhao

Keywords: Recommendation System

TL;DR: This paper proposes a union-interaction mechanism to enhance the semantic matching performance between query and document in e-commerce search systems, addressing the limitations of conventional representation-based models.

Abstract: For most practical search systems, the cascaded matching-prerank-rank architecture is designed. In the prerank stage, the dual-tower structure is widely used to maintain efficiency. However, due to the lack of interaction between query and document, this architecture could only take into account efficiency but not both effectiveness and efficiency. Inspired by this, we propose a simple but effective dual-tower model: uni-match, which has the efficiency of dual-tower model and the effectiveness close to that of cross model. Sufficient offline and online experiments show the effectiveness of our proposed method. Currently, the Uni-match model has been deployed in the search system of a shortvideo App, providing daily services to hundreds of millions users.