为日本二手平台优化搜索，用领域嵌入提升查询相关性。
Towards Better Search with Domain-Aware Text Embeddings for C2C Marketplaces
- 用购买导向的查询-标题对微调，加角色前缀建模查询与商品差异。
- 在历史日志上效果优于通用编码器，替换PCA后提升更显著。
- 适合做电商搜索优化，尤其关注专有名词和术语重要性匹配。
消费者对消费者（C2C）电商平台面临独特检索挑战：查询短而模糊、用户生成的商品信息嘈杂，且受生产环境严格限制。本文报告了我们在日本最大C2C平台Mercari上构建领域感知的日文文本嵌入方法以改善搜索质量的实验。通过使用以购买为导向的查询-标题配对进行微调，并引入角色特定前缀来建模查询与商品之间的不对称性。为满足生产约束，采用马特罗什卡表示学习（Matryoshka Representation Learning）获取紧凑且抗截断的嵌入。基于历史搜索日志的离线评估显示，该方法持续优于强基线通用编码器，尤其是在用马特罗什卡截断替代PCA压缩时提升明显。人工评估进一步表明其对专有名词、平台特定语义及术语重要性对齐的更好处理能力。此外，初步在线A/B测试显示用户收入和搜索流程效率均有统计显著提升，交易频率保持稳定。结果表明，领域感知嵌入在大规模下提升了搜索相关性与效率，为大模型时代更丰富的搜索体验奠定了实用基础。
原文摘要 · Abstract (English)
Consumer-to-consumer (C2C) marketplaces pose distinct retrieval challenges: short, ambiguous queries; noisy, user-generated listings; and strict production constraints. This paper reports our experiment to build a domain-aware Japanese text-embedding approach to improve the quality of search at Mercari, Japan's largest C2C marketplace. We experimented with fine-tuning on purchase-driven query-title pairs, using role-specific prefixes to model query-item asymmetry. To meet production constraints, we apply Matryoshka Representation Learning to obtain compact, truncation-robust embeddings. Offline evaluation on historical search logs shows consistent gains over a strong generic encoder, with particularly large improvements when replacing PCA compression with Matryoshka truncation. A manual assessment further highlights better handling of proper nouns, marketplace-specific semantics, and term-importance alignment. Additionally, an initial online A/B test demonstrates statistically significant improvements in revenue per user and search-flow efficiency, with transaction frequency maintained. Results show that domain-aware embeddings improve relevance and efficiency at scale and form a practical foundation for richer LLM-era search experiences.
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。