ISEE：数据库字段的交互式语义丰富
ISEE: Interactive Semantic Enrichment for Database Fields
- Purdue University（普渡大学）
- Adobe（奥多比公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出ISEE系统，通过评分、收集领域知识并与用户协作丰富数据库字段语义，可降低认知负荷、提升描述质量并增强下游任务性能。
AI中文摘要：
基于大语言模型（LLM）的智能体正越来越多地被部署到与数据相关的任务中，包括数据感知、探索与检索。然而，它们的性能高度依赖于数据语义的清晰性与完整性。在实际应用中，许多字段描述仍存在模糊或不完整的问题，因为大量关键上下文（如自定义字段的含义）源自用户的领域知识，且很少被公开记录。这一差距限制了智能体在下游任务（如实体链接）中的表现。为弥合该差距，我们提出了一种新颖且全面的交互式语义丰富系统（Interactive SEmantic Enrichment，ISEE）。给定一个数据字段描述，ISEE通过评分系统评估其质量，收集领域知识，并与用户协作丰富语义。通过用户研究、自动化用户模拟、定量评估与案例研究，我们证明ISEE可显著降低认知负荷、提升描述质量并增强下游任务性能。
英文摘要：
LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their performance heavily depends on the clarity and completeness of data semantics. In practice, many field descriptions remain ambiguous or incomplete, as much of the essential context (e.g., the meaning of a customized field) originates from users' domain knowledge and is rarely documented publicly. This gap restricts the agents' task performance in downstream tasks, such as entity-linking. To bridge this gap, we introduce a novel and comprehensive Interactive SEmantic Enrichment system (ISEE). Given a data field description, ISEE measures its quality through a scoring system, gathers domain knowledge, and collaboratively enriches the semantics with users. Through a user study, automated user simulation, quantitative evaluation, and case study, we demonstrate that ISEE significantly reduces cognitive load, improves description quality, and enhances downstream task performance.
