Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Maoqi, Fang, Quan, Yang, Yang, Zhao, Can, Cai, Kaiquan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.12630
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911268412063744
author Liu, Maoqi
Fang, Quan
Yang, Yang
Zhao, Can
Cai, Kaiquan
author_facet Liu, Maoqi
Fang, Quan
Yang, Yang
Zhao, Can
Cai, Kaiquan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing
Liu, Maoqi
Fang, Quan
Yang, Yang
Zhao, Can
Cai, Kaiquan
Computation and Language
Artificial Intelligence
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.
title Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.12630