Embedding-based Product Retrieval in Taobao Search

TL;DR

This paper introduces MGDSPR, a novel embedding-based product retrieval model for Taobao Search that improves relevance and convergence, addressing issues of relevance and training-inference discrepancy in existing systems.

Contribution

The paper proposes MGDSPR, a new retrieval model that enhances relevance and training efficiency, with practical deployment insights for large-scale e-commerce search systems.

Findings

Significant offline metric improvements in product relevance.

Successful online A/B test results demonstrating system effectiveness.

Effective handling of noisy data and hard negatives without extra resources.

Abstract

Nowadays, the product search service of e-commerce platforms has become a vital shopping channel in people's life. The retrieval phase of products determines the search system's quality and gradually attracts researchers' attention. Retrieving the most relevant products from a large-scale corpus while preserving personalized user characteristics remains an open question. Recent approaches in this domain have mainly focused on embedding-based retrieval (EBR) systems. However, after a long period of practice on Taobao, we find that the performance of the EBR system is dramatically degraded due to its: (1) low relevance with a given query and (2) discrepancy between the training and inference phases. Therefore, we propose a novel and practical embedding-based product retrieval model, named Multi-Grained Deep Semantic Product Retrieval (MGDSPR). Specifically, we first identify the inconsistency between the training and inference stages, and then use the softmax cross-entropy loss as the training objective, which achieves better performance and faster convergence. Two efficient methods are further proposed to improve retrieval relevance, including smoothing noisy training data and generating relevance-improving hard negative samples without requiring extra knowledge and training procedures. We evaluate MGDSPR on Taobao Product Search with significant metrics gains observed in offline experiments and online A/B tests. MGDSPR has been successfully deployed to the existing multi-channel retrieval system in Taobao Search. We also introduce the online deployment scheme and share practical lessons of our retrieval system to contribute to the community.