企业系统中领域特定检索的困难负样本挖掘
Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems
AI总结：
针对企业搜索中的语义不匹配问题，提出可扩展的困难负样本挖掘框架，集成多种嵌入模型并动态选择困难负样本，在专有语料库上显著提升MRR，并在公共数据集上验证了泛化性。
摘要：
企业搜索系统常因语义不匹配和术语重叠而难以检索到准确的领域特定信息。这些问题会降低下游应用（如知识管理、客户支持和检索增强生成代理）的性能。为应对这一挑战，我们提出了一种专门针对领域特定企业数据的可扩展困难负样本挖掘框架。我们的方法动态选择语义上具有挑战性但上下文不相关的文档，以增强部署的排序模型。我们的方法集成了多种嵌入模型，进行降维，并独特地选择困难负样本，确保计算效率和语义精度。在我们专有的企业语料库（云服务领域）上的评估显示，与最先进的基线和其它负采样技术相比，MRR@3 提升了 15%，MRR@10 提升了 19%。在公共领域特定数据集（FiQA、Climate Fever、TechQA）上的进一步验证证实了我们的方法的泛化能力和对实际应用的适用性。
英文摘要：
Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge management, customer support, and retrieval-augmented generation agents. To address this challenge, we propose a scalable hard-negative mining framework tailored specifically for domain-specific enterprise data. Our approach dynamically selects semantically challenging but contextually irrelevant documents to enhance deployed re-ranking models. Our method integrates diverse embedding models, performs dimensionality reduction, and uniquely selects hard negatives, ensuring computational efficiency and semantic precision. Evaluation on our proprietary enterprise corpus (cloud services domain) demonstrates substantial improvements of 15\% in MRR@3 and 19\% in MRR@10 compared to state-of-the-art baselines and other negative sampling techniques. Further validation on public domain-specific datasets (FiQA, Climate Fever, TechQA) confirms our method's generalizability and readiness for real-world applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
