CrimeNER Demo Platform Launched for Crime-Related Entity Recognition

Miguel Lopez-Duran, Julian Fierrez, Aythami Morales, Daniel DeAlcala, Gonzalo Mancera, Javier Irigoyen, Ruben Tolosana, Oscar Delgado, Francisco Jurado, Alvaro Ortigosa· July 17, 2026 View original

Summary

CrimeNER Demo is an AI platform designed for extracting and classifying crime-related information from documents using Named-Entity Recognition (NER). It offers pre-trained models and allows users to fine-tune models with their own data for specific use cases.

A new AI-powered platform, CrimeNER Demo, has been introduced to facilitate Named-Entity Recognition (NER) specifically within the crime domain. This tool allows users to automatically extract and categorize general crime-related entities from various documents, providing two levels of granularity for classification. The platform comes equipped with pre-trained NER models based on the CrimeNER database. Additionally, it offers the flexibility for users to upload and annotate their own data, enabling them to train custom models tailored to their unique requirements. This demonstrator aims to advance crime-related NER research and serve as a practical resource for both researchers and law enforcement agencies.

Why it matters

This tool can significantly enhance the efficiency of information extraction from large volumes of crime-related text, aiding law enforcement and researchers in analysis and investigation.

How to implement this in your domain

  1. 1Access the CrimeNER Demo platform and explore its pre-trained models for initial use cases.
  2. 2Identify specific crime document types within your organization that could benefit from automated entity extraction.
  3. 3Gather and annotate a small dataset relevant to your specific needs to fine-tune the models.
  4. 4Integrate the refined NER capabilities into existing investigative or analytical workflows.

Who benefits

Law EnforcementLegalGovernmentJournalismResearch

Key takeaways

  • CrimeNER Demo provides specialized NER for extracting crime-related information.
  • Users can leverage pre-trained models or fine-tune them with custom data.
  • The platform aims to support both research and practical applications in law enforcement.
  • It offers an automated pipeline to extract and annotate crime entities from documents.

Original post by Miguel Lopez-Duran, Julian Fierrez, Aythami Morales, Daniel DeAlcala, Gonzalo Mancera, Javier Irigoyen, Ruben Tolosana, Oscar Delgado, Francisco Jurado, Alvaro Ortigosa

"arXiv:2607.14800v1 Announce Type: new 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…"

View on X

Originally posted by Miguel Lopez-Duran, Julian Fierrez, Aythami Morales, Daniel DeAlcala, Gonzalo Mancera, Javier Irigoyen, Ruben Tolosana, Oscar Delgado, Francisco Jurado, Alvaro Ortigosa on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses