Sep 2026· Proceedings of the 20th ACM Conference on Recommender Systems· 0 citations· 19 references
TL;DR
TSSR-Beta (Taobao Search Semantic Retrieval Model - Beta), which improves the expressiveness of the production Dual-Encoder TSSR through a plug-in similarity module, termed the Hybrid Interaction Head, which introduces fine-grained matching in the representation space through two complementary pathways.
Abstract
Semantic retrieval in e-commerce search aims to identify a compact candidate set from billion-scale product catalogs with both high recall and low latency. Dual-Encoders dominate this stage due to their efficient dot-product similarity, but this formulation limits model expressiveness and fails to capture fine-grained relationships between queries and items. While prior work has explored interaction-based similarity, its additional cost often prevents deployment at industrial scale. We present TSSR-Beta (Taobao Search Semantic Retrieval Model - Beta), which improves the expressiveness of our production Dual-Encoder TSSR through a plug-in similarity module, termed the Hybrid Interaction Head. This module introduces fine-grained matching in the representation space through two complementary pathways: InteractMLP, which captures explicit matching patterns with residual MLP blocks, and InteractTrans, which models implicit cross-dimensional interactions with a Transformer layer. Their outputs are combined by a Fusion Head to produce the final similarity score. TSSR-Beta introduces only a small parameter overhead to the Dual-Encoder without changing its architecture, enabling it to be (1) pluggable, readily adapting to diverse Dual-Encoder backbones; (2) efficiently trainable, supporting large-batch contrastive learning with massive negative sampling; and (3) industrially deployable, preserving offline item pre-encoding and supporting low-latency online retrieval with Neighborhood-Aware Approximate Nearest Neighbor (NANN). Offline experiments on the Taobao Search show a +3.90pp Hitrate@500 improvement over TSSR. On public Natural Questions and WebQA, our module further improves Recall@1 by +4.60pp and +0.90pp over public Dual-Encoder, respectively. Deployed in Taobao Search, TSSR-Beta delivers low-latency billion-scale retrieval and achieves +0.63% transaction count and +2.69% GMV gains in online A/B tests.
The paper addresses the gap between general-purpose embedding benchmarks and enterprise job-candidate matching constraints, providing a structured basis for comparing embedding strategies under realistic job-candidate retrieval conditions.
Sai Yashwant, Siddhartha Jain, Anurag Dubey et al.· 0 citations
VARG, a generative retrieval system for Tmall App search that directly admits generated item candidates to the existing final ranker and improves GMV, per-user IPV, and PCTR and online shopping-guide query evaluations further show that VARG maintains competitive relevance with a smaller candidate quota.
Xiao-Peng Chu, Jian-Bo Zhu, Ming-Min Jin et al.· arXiv.org· 1 citation
The results show that a shared semantic product hierarchy can support both recommendation and search while preserving the task-specific context required by each application.
Steven Xu, Sanjyot Thete, Saathvik Dirisala et al.· 0 citations
ConRAG is proposed, a novel enhanced RAG framework to establish an information connection between retrievers and LLMs in RAG, thereby enhancing relationship modeling of LLMs and is suitable for low-resource scenarios where LLMs and retrievers are frozen.
Fu-Da Ye, Shuang-Yin Li, Yong-Qi Zhang et al.· ACM Transactions on Knowledg...· 0 citations
E-commerce search often suffers from vocabulary mismatch between user queries and merchant-authored product titles, since short titles cannot fully cover diverse user expressions or visual product attributes. Although Doc2Query alleviates this issue by generating pseudo-queries for document expansion, traditional metho...
Hui Zhou, Jianhui Ji, Lei Ma et al.· ACM International Conference...· 0 citations
This study proposes STaR, a novel retriever fine-tuning framework that integrates BM25 similarity graph-based soft labeling with a triplet similarity learning strategy based on Sentence-BERT (SBERT), and introduces a triplet-aware SBERT training architecture that explicitly models relative semantic distances between qu...
Jiali Jiang, Chih-Yung Chang, Youxi Li et al.· Multimedia Systems· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.