Learning Multi-Stage Multi-Grained Semantic Embeddings for E-Commerce Search

Abstract

Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) methods are prevailing. These methods adopt a two-tower framework to learn embedding vectors for query and item separately and thus leverage efficient approximate nearest neighbor (ANN) search to retrieve relevant items. However, existing EBR methods usually ignore inconsistent user behaviors in industrial multi-stage search systems, resulting in insufficient retrieval efficiency with a low commercial return. To tackle this challenge, we propose to improve EBR methods by learning Multi-level Multi-Grained Semantic Embeddings(MMSE). We propose the multi-stage information mining to exploit the ordered, clicked, unclicked and random sampled items in practical user behavior data, and then capture query-item similarity via a post-fusion strategy. We then propose multi-grained learning objectives that integrate the retrieval loss with global comparison ability and the ranking loss with local comparison ability to generate semantic embeddings. Both experiments on a real-world billion-scale dataset and online A/B tests verify the effectiveness of MMSE in achieving significant performance improvements on metrics such as offline recall and online conversion rate (CVR).

References in corpus (7)

• Decoupled Weight Decay Regularization
• Embedding-based Retrieval in Facebook Search
• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• Cascade Ranking for Operational E-commerce Search
• Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval
• ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval
• Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval

Cited by in corpus (1)

• Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model