Computational linguistics for defence and security applications
Cross-faculty collaboration between University of Leeds' research groups
Resources and results
We develop a framework for intelligent real-time detection and analysis of suspected security threats in electronic communication across different languages. Our approach combines machine translation (MT), information extraction (IE) and text similarity detection technologies that will be applied to a corpus of electronic communication in suspected terrorist networks on social media, websites, comments and blogs used for radicalization and terrorist propaganda.
The project is in its initial stage. We invite partners for collaboration nationally and internationally.
We are interested in cross disciplinary collaboration in the areas such as (but not limited to):
- Community response to propaganda threats
- Beyond security analysts: anti-terrorist volunteers and crowd intelligence
- Automatic creation of IE propaganda templates
- Template similarity and event similarity detection; argumentative texts
- Learning defence and security ontologies from corpora
- Automated reasoning using ontologies (predicate & description logic)
- Modeling language distortion for real-world communication
- Dialectal, graphical variation, misspelling, abbreviations
- MT and IE for non-literal language usage
- metaphors, euphemisms, indirect references
Babych, B and Atwell, E (2015). Multilingual Information Extraction framework for real-time detection of terrorist propaganda threats in on-line communication. In: Proc. of XI International Conference "Military education and science: the present and the future" Military Institute of Taras Shevchenko National University, 27 November 2015, Kyiv, Ukraine. [book of abstracts]. Abrstact (en) [pdf]; Abstract (uk) [pdf]; Powerpoint (en) [ppt]; Powerpoint (uk) [ppt]
Brierley C; Atwell ES; Rowland C; Anderson J. (2013). Semantic pathways: a novel visualisation of varieties of English. ICAME Journal of the International Computer Archive of Modern English, vol. 37, pp.5-36. (A deliverable of the "Detecting Terrorist Activities: Making Sense" project)[pdf]
IDEAS Factory - Detecting Terrorist Activities: Making Sense, funded by EPSRC/ESRC/CPNI
The Artificial Intelligence Research Group (School of Computing, Co-I Eric Atwell) was part of the consortium in the project, which has developed an intelligent decision-support system that is able to apply the logic used by detectives to identify suspicious behaviour for countering terrorist activity.
The key challenge addressed by the project is the analysis and visualization of multiple sources of multi-modal data that may be partial, unreliable and contradictory. The project created an interactive visualization-based decision support assistant, which collects data, fuses it, analyses it and visualizes the results in a way which can be shared by analysts.
Bogdan Babych: email: b.babych(at)leeds.ac.uk; web: http://corpus.leeds.ac.uk/bogdan/
Eric Atwell: email: e.s.atwell(at)leeds.ac.uk; web: https://engineering.leeds.ac.uk/staff/33/Dr_Eric_Atwell