CrimeNER Demo: Named-Entity Recognition in the Crime Domain

2026-07-16

AI Summary

This work addresses the lack of customizable and user-friendly named entity recognition (NER) tools tailored for the criminal justice domain. To bridge this gap, the authors present CrimeNER Demo, an open-source NER platform specifically designed for crime-related texts, which introduces the first end-to-end automated annotation pipeline supporting two-level granularity in entity classification. Built upon pre-trained language models, the platform leverages transfer learning and fine-tuning mechanisms, enabling seamless integration of pre-trained models while allowing users to adapt them with their own annotated data. By offering a publicly accessible, ready-to-use tool for extracting structured information from unstructured crime narratives, CrimeNER Demo significantly advances both practical applications and academic research in criminal text analysis.

Abstract

We present CrimeNER Demo, an AI-powered platform that enables us to extract general crime-related information from documents and classify them into entity types with two levels of granularity. We provide pretrained NER models on the CrimeNER database, and we give the possibility to users to provide their own annotated data to train models for their own specific cases. This demonstrator aims to promote crime-related NER research and provides a practical tool to automatically extract crime information for researchers and law enforcement agencies. The demonstrator includes: i) Pretrained NER models on the crime domain; ii) Possibility to finetune the models on specific data annotated by the user; and iii) An automatic pipeline to extract and annotate crime entities from documents. The demo platform, a tutorial to run the demo, and a video demonstration are publicly available on GitHub.

Problem

• Named-Entity Recognition
• Crime Domain
• Entity Classification
• Information Extraction

Innovation

• Named Entity Recognition
• Crime Domain
• Pretrained Models
• Model Fine-tuning
• Automated Annotation Pipeline