Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports

TL;DR

This paper presents a symbolic framework that converts natural language law enforcement narratives into structured, evidence-linked facts and temporal graphs for improved understanding and reasoning.

Contribution

It introduces a novel approach combining semantic parsing, ontology mapping, and reasoning to extract incident details from unstructured reports.

Findings

54.1% of extracted events had high confidence scores (≥0.80)

93.7% of events mapped through semantic paths involving PropBank, VerbNet, and WordNet

100% agreement on incident initiation, stolen items, and temporal cues

Abstract

Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. We propose a framework using symbolic methods for converting narratives into evidence-linked facts. Our objective is to measure the value of narratives to recover incident details only from the unstructured text and build temporal graphs with time cues and domain axioms. We achieve this by redacting personal identifiers, semantic parsing, predicate mapping to ontology, and reasoning. We evaluate the symbolic approach on 450 property crime reports and a short human review. Of the extracted events from the system, 54.1% had a confidence score of at least 0.80 and 93.7% were mapped through the PropBank--VerbNet--WordNet semantic path. 100% agreement was reached on incident initiation, stolen items, and temporal cues and lower agreement for forced entry interpretation.