Extracting Meaningful Entities from Police Narrative Reports
(2002) Extracting Meaningful Entities from Police Narrative Reports. In Proceedings National Conference for Digital Government Research, Los Angeles, CA.
Full text available as: |
Abstract
Valuable criminal-justice data in free texts such as police narrative reports are currently difficult to be accessed and used by intelligence investigators in crime analyses. It would be desirable to automatically identify from text reports meaningful entities, such as person names, addresses, narcotic drugs, or vehicle names to facilitate crime investigation. In this paper, we report our work on a neural network-based entity extractor, which applies named-entity extraction techniques to identify useful entities from police narrative reports. Preliminary evaluation results demonstrated that our approach is feasible and has some potential values for real-life applications. Our system achieved encouraging precision and recall rates for person names and narcotic drugs, but did not perform well for addresses and personal properties. Our future work includes conducting larger-scale evaluation studies and enhancing the system to capture human knowledge interactively.
| EPrint Type: | Conference Paper |
|---|---|
| Keywords: | National Science Digital Library, NSDL, Artificial Intelligence Lab, AI Lab, Extraction |
| Subjects: | Knowledge Management Data Mining Information Seeking Behaviors |
| ID Code: | 423 |
| Deposited On: | 16 August 2004 |
| Alternative Locations: | http://ai.bpa.arizona.edu/go/papers.html |
| Eprint Statistics: | View statistics for this eprint |
| Tell A Colleague: | Tell a colleague about it. |