Intelligence analysis software
The ARGA project, funded by the Defence and Security Accelerator (DASA), sought to apply structure to natural language text data contained in day-to-day documents (such as emails and reports). This would enable the valuable information in such material to be searched and retrieved more easily in the future.
The project required the development of a prototype text mark up and analysis tool that could work in real time and in partnership with intelligence analyst users (human-machine teaming) using cutting-edge machine learning (ML) and natural language processing (NLP) methods.
The tool would offer suggestions to an author as they were creating a report, nominating the most salient entities, events and relationships to capture for further analysis. The writer would be able to accept or reject these suggestions and the ML routines would learn from this feedback to fine-tune future recommendations.
Working together with strategic partners (Committed Software Ltd, Aleph Insights Ltd and Bricolage), the project team specified, designed, developed and tested the ARGA adaptive report generation tool that could work seamlessly with report producers to capture key information in real time.
Bricolage had specific responsibilities for drafting the functional specification, development of the Schema and Ontology; designing , planning and administering the product trial; and analysis of trial data.
The project delivered a working prototype tool to the MOD. The software fulfilled requirements by allowing users to give feedback on automated processes of text markup, which gave the system additional information that allowed it to learn and develop more accurate suggestions for the future. The end result was that the data in regular natural language reports could be pre-structured to make it suitable for immediate analysis and unlock its value for future use. Analysts were thereby able to make better decisions more quickly.
ARGA: Adaptive Report Generation Assistant
The Project
ARGA is being funded through the Defence and Security Accelerator under the ‘Revolutionise the Human Information Relationship for Defence’ call. It aims to solve the information management and analysis problems stemming from the use of unstructured natural language text.
What does ARGA do?
Across the whole of Defence, large amounts of text data are routinely produced in an unstructured format, limiting data retrieval and impeding optimal decision-making. ARGA seeks to reduce the burden this creates at source by intelligently assisting authors to apply meaningful structure to text as they write, ultimately creating an adaptive information bridge between data producers and data consumers.
Without a means of structuring text, most documents end up in ‘data landfills’ after they have been exploited for their primary purpose. Emails languish in mail servers, reports fill up SharePoint sites and vital conversations become buried within burgeoning threads on group messaging platforms. In this form, these sources of text cannot be exploited to generate insights. Further, any attempts to retrospectively structure them are manpower intensive, boring and difficult.
