DILAB团队构建多语言电商搜索系统，5强成绩验证其数据优化与模型迭代的有效性。
Alibaba International E-commerce Product Search Competition DILAB Team Technical Report
- 分阶段流水线：数据清洗、轻量预处理、自适应建模协同提升
- 综合得分0.8819，在查询-品类与查询-商品任务上表现均衡
- 适合关注多语言电商搜索系统设计与工程优化的开发者
本文介绍由DILAB团队开发的多语言电商搜索系统，在最终排行榜中获得第5名，综合得分达0.8819，各项评估指标表现稳定且优异。为应对多语言查询与商品理解的挑战，团队设计了包含数据精炼、轻量预处理和自适应建模的多阶段流程。数据精炼阶段提升了数据集的一致性和品类覆盖度，通过语言标签标注与噪声过滤改善输入质量。建模阶段探索多种架构与微调策略，并利用精心筛选的验证集优化超参数，实现查询-品类（QC）与查询-商品（QI）任务间的性能平衡。该框架在不同语言与领域下均表现出鲁棒性与适应性，凸显系统化数据治理与迭代评估对多语言搜索系统的重要性。源码已公开于 https://github.com/2noweyh/DILAB-Alibaba-Ecommerce-Search。
原文摘要 · Abstract (English)
This study presents the multilingual e-commerce search system developed by the DILAB team, which achieved 5th place on the final leaderboard with a competitive overall score of 0.8819, demonstrating stable and high-performing results across evaluation metrics. To address challenges in multilingual query-item understanding, we designed a multi-stage pipeline integrating data refinement, lightweight preprocessing, and adaptive modeling. The data refinement stage enhanced dataset consistency and category coverage, while language tagging and noise filtering improved input quality. In the modeling phase, multiple architectures and fine-tuning strategies were explored, and hyperparameters optimized using curated validation sets to balance performance across query-category (QC) and query-item (QI) tasks. The proposed framework exhibited robustness and adaptability across languages and domains, highlighting the effectiveness of systematic data curation and iterative evaluation for multilingual search systems. The source code is available at https://github.com/2noweyh/DILAB-Alibaba-Ecommerce-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。