统一餐品、店铺与零售商品的多语言语义搜索，召回率显著提升。
Scaling Multilingual Semantic Search in Uber Eats Delivery
- 用数亿条查询-文档交互数据微调双塔模型，融合多种损失函数。
- 在六个市场、三个垂直领域上，召回率远超基线模型。
- 支持单模型服务多种嵌入尺寸，适合生产级多语言搜索系统。
我们提出一个面向 Uber Eats 的生产级语义检索系统，统一了店铺、菜品及生鲜/零售商品的检索。该方法基于 Qwen2 双塔模型，利用数亿条预训练阶段聚合并匿名化的查询-文档交互数据进行微调。采用批次内负样本的 InfoNCE 与困难负样本的 triplet-NCE 损失联合训练，并引入马特里什卡表示学习（Matryoshka Representation Learning, MRL）实现单模型支持多种嵌入维度。系统在六个市场和三个垂直领域上均显著优于强基线。本文涵盖数据清洗、模型架构、大规模训练与评估全流程，并分享构建统一、多语言、多垂直领域的消费者搜索系统的实用经验。
原文摘要 · Abstract (English)
We present a production-oriented semantic retrieval system for Uber Eats that unifies retrieval across stores, dishes, and grocery/retail items. Our approach fine-tunes a Qwen2 two-tower base model using hundreds of millions of query-document interactions that were aggregated and anonymized pretraining. We train the model with a combination of InfoNCE on in-batch negatives and triplet-NCE loss on hard negatives, and we leverage Matryoshka Representation Learning (MRL) to serve multiple embedding sizes from a single model. Our system achieves substantial recall gains over a strong baseline across six markets and three verticals. This paper presents the end to end work including data curation, model architecture, large-scale training, and evaluation. We also share key insights and practical lessons for building a unified, multilingual, and multi-vertical retrieval system for consumer search.
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。