Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search
Gui Ling (Taobao & · Tmall Group of Alibaba) · Tmall Group of Alibaba) · Wenjun Peng (Taobao & · Yue Jiang (Taobao & · Dongshuai Li (Taobao & · Wenjun Peng (Taobao & · Chenhe Dong (Taobao & · Xingxian Liu (Taobao & · Shengjie Sun (Taobao & · Dongshuai Li (Taobao & · Shengjie Sun (Taobao & · Fuyu Lv (Taobao & · Shengjie Sun (Taobao & · Chenhe Dong (Taobao & · Shengjie Sun (Taobao & · Xingxian Liu (Taobao & · Shengjie Sun (Taobao &
摘要
Product retrieval is the backbone of e-commerce search: for each user query, it identifies a high-recall candidate set from billions of items, laying the foundation for high-quality ranking and user experience. Despite extensive optimization for mainstream queries, existing systems still struggle...