构建1.2万条专家标注的NOTAM数据集，提升飞行安全信息自动解析能力
Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing
- 用多智能体协作框架构建高质量专家标注数据集
- 在194个航管区的1.2万条NOTAM上实现语义解析性能提升
- 适合航空安全、自然语言处理方向研究者参考
航行通告（NOTAM）是传递关键飞行安全信息的重要渠道，但其复杂的语言结构和隐含推理给自动化解析带来挑战。现有研究多聚焦于分类和命名实体识别等表面任务，缺乏深层语义理解。为此，我们提出NOTAM语义解析任务，强调语义推断与航空领域知识融合，生成结构化且富含推理的信息输出。为此，我们构建了Knots（Knowledge and NOTAM Semantics）数据集，包含12,347条专家标注的NOTAM，覆盖194个飞行情报区，并通过多智能体协同框架实现全面领域发现。我们系统评估多种提示工程策略与模型适配技术，在航空文本理解与处理上取得显著提升。实验结果验证了该方法的有效性，为自动化NOTAM分析系统提供了重要参考。代码已开源：https://github.com/Estrellajer/Knots。
原文摘要 · Abstract (English)
Notice to Air Missions (NOTAMs) serve as a critical channel for disseminating key flight safety information, yet their complex linguistic structures and implicit reasoning pose significant challenges for automated parsing. Existing research mainly focuses on surface-level tasks such as classification and named entity recognition, lacking deep semantic understanding. To address this gap, we propose NOTAM semantic parsing, a task emphasizing semantic inference and the integration of aviation domain knowledge to produce structured, inference-rich outputs. To support this task, we construct Knots (Knowledge and NOTAM Semantics), a high-quality dataset of 12,347 expert-annotated NOTAMs covering 194 Flight Information Regions, enhanced through a multi-agent collaborative framework for comprehensive field discovery. We systematically evaluate a wide range of prompt-engineering strategies and model-adaptation techniques, achieving substantial improvements in aviation text understanding and processing. Our experimental results demonstrate the effectiveness of the proposed approach and offer valuable insights for automated NOTAM analysis systems. Our code is available at: https://github.com/Estrellajer/Knots.
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。