通过预测用户查询类别并聚焦匹配品类，提升电商搜索相关性。
Improving E-commerce Search with Category-Aligned Retrieval
- 用查询嵌入生成可训练的品类原型，精准预测用户想找的品类。
- 使用OpenAI模型后，品类预测准确率从43.8%提升至83.2%。
- 适合需要高精度品类定位的电商搜索系统，需配合自适应策略使用。
传统电商搜索系统常因用户查询与商品目录之间的语义鸿沟而表现不佳。本文提出类别对齐检索系统（CARS），先预测用户查询所属的产品品类，再增强该品类内的商品召回。我们引入一种新方法，从查询嵌入中构建‘可训练品类原型’。在两个模型上评估：轻量级 all-MiniLM-L6-v2 和 OpenAI text-embedding-ada-002。离线评估显示效果显著：使用 OpenAI 模型后，Top-3 品类预测准确率从零样本基线的 43.8% 提升至 83.2%。然而，端到端模拟揭示了盲目应用品类增强的局限性：尽管预测准确率高，但直接集成可能降低 nDCG@10 等相关性指标。这主要源于数据集中的歧义问题（如 Amazon ESCI 语料库中的多义查询）以及检索系统对过度约束过滤器的敏感性。关键在于，这些结果并不否定该方法价值，反而强调需采用置信度感知和自适应的集成策略。
原文摘要 · Abstract (English)
Traditional e-commerce search systems often struggle with the semantic gap between user queries and product catalogs. In this paper, we propose a Category-Aligned Retrieval System (CARS) that improves search relevance by first predicting the product category from a user's query and then boosting products within that category. We introduce a novel method for creating "Trainable Category Prototypes" from query embeddings. We evaluate this method with two models: a lightweight all-MiniLM-L6-v2 and OpenAI's text-embedding-ada-002. Our offline evaluation shows this method is highly effective, with the OpenAI model increasing Top-3 category prediction accuracy from a zero-shot baseline of 43.8% to 83.2% after training. The end-to-end simulation, however, highlights the limitations of blindly applying category boosts in a complex retrieval pipeline: while accuracy is high, naive integration can negatively affect search relevance metrics such as nDCG@10. We argue that this is partly due to dataset-specific ambiguities (e.g., polysemous queries in the Amazon ESCI corpus) and partly due to the sensitivity of retrieval systems to over-constraining filters. Crucially, these results do not diminish the value of the approach; rather, they emphasize the need for confidence-aware and adaptive integration strategies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。