A Real-Time System to Populate FRA Form 57 from News

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lim, Chansong, Shahgir, Haz Sameen, Dong, Yue, Chen, Jia, Papalexakis, Evangelos E.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911340757516288
author Lim, Chansong
Shahgir, Haz Sameen
Dong, Yue
Chen, Jia
Papalexakis, Evangelos E.
author_facet Lim, Chansong
Shahgir, Haz Sameen
Dong, Yue
Chen, Jia
Papalexakis, Evangelos E.
contents Local railway committees need timely situational awareness after highway-rail grade crossing incidents, yet official Federal Railroad Administration (FRA) investigations can take days to weeks. We present a demo system that populates Highway-Rail Grade Crossing Incident Data (Form 57) from news in real time. Our approach addresses two core challenges: the form is visually irregular and semantically dense, and news is noisy. To solve these problems, we design a pipeline that first converts Form 57 into a JSON schema using a vision language model with sample aggregation, and then performs grouped question answering following the intent of the form layout to reduce ambiguity. In addition, we build an evaluation dataset by aligning scraped news articles with official FRA records and annotating retrievable information. We then assess our system against various alternatives in terms of information retrieval accuracy and coverage.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Real-Time System to Populate FRA Form 57 from News
Lim, Chansong
Shahgir, Haz Sameen
Dong, Yue
Chen, Jia
Papalexakis, Evangelos E.
Information Retrieval
Local railway committees need timely situational awareness after highway-rail grade crossing incidents, yet official Federal Railroad Administration (FRA) investigations can take days to weeks. We present a demo system that populates Highway-Rail Grade Crossing Incident Data (Form 57) from news in real time. Our approach addresses two core challenges: the form is visually irregular and semantically dense, and news is noisy. To solve these problems, we design a pipeline that first converts Form 57 into a JSON schema using a vision language model with sample aggregation, and then performs grouped question answering following the intent of the form layout to reduce ambiguity. In addition, we build an evaluation dataset by aligning scraped news articles with official FRA records and annotating retrievable information. We then assess our system against various alternatives in terms of information retrieval accuracy and coverage.
title A Real-Time System to Populate FRA Form 57 from News
topic Information Retrieval
url https://arxiv.org/abs/2512.22457