Abstract
The relation extraction of crime news can help the monitoring specialists to accelerate the crime investigation. However, constructing patterns or designing templates manually requires domain experts. Also the built patterns do not guarantee complete differentiation among different relation instances. The automatic detection of crime entities and relationship among entities can help the regulatory authorities to accelerate the crime investigation and decision support instead of being reliant on manual process. This study aims to increase the effectiveness of the extraction of crime entities and relationship among entities based on the determination of crime lingusitic pattern using Minimal Differentiator Expressions (MDEs) that represent the cases that will be used by the CBR classifier. The proposed extraction methods can help in compiling a highly accurate and machine-understandable crime knowledge bases which can support the regulatory authorities' investigation. This paper conducted on our proposed MDEs algorithm for linguistic pattern reuse in CBR approaches.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.