From Fact Extraction to Report Generation

CSRI’s Federico Cerutti presented the paper “ from Fact Extraction to Report generation” at the 7th International Conference on Computational Models of Argument. is a system that supports the full data-to-decision process from information extraction, to hypotheses formation, to report generation that can be used for briefings to inform decision-makers. facilitates sensemaking within the intelligence analysis process in a declarative format. Intelligence analysis is an iterative process of foraging for information and sensemaking in which the analysis structure increases incrementally from a shoebox of information, through evidence files, to the generation and evaluation of hypotheses. provides a method to record and support the process of forming hypotheses from the relationships among information which enables the analyst to highlight information or assumptions that may lead to interrelated as well as alternative hypotheses. makes this core process of reasoning explicit, providing further support for structuring reasoning and mitigating biases. The reasoning mechanism identifies what evidence and claims together constitute a plausible interpretation of an analysis.

Federico Cerutti also co-authored the paper “Probabilistic Graded Semantics” with Matthias Thimm and Tjitze Rienstra, that was also presented at the same conference.

This work is part of the DAIS ITA project at CSRI.