Explanation Container in Case-Based Biomedical Question-Answering
This work addresses the need for interpretability in biomedical data systems for translational scientists, though it appears incremental as it builds upon existing knowledge containers.
The paper tackles the problem of providing explanations for biomedical question-answering by designing an Explanatory Agent (xARA) within the Biomedical Data Translator, which answers queries by ranking results and explaining the rankings using a novel Explanation Container.
The National Center for Advancing Translational Sciences(NCATS) Biomedical Data Translator (Translator) aims to attenuate problems faced by translational scientists. Translator is a multi-agent architecture consisting of six autonomous relay agents (ARAs) and eight knowledge providers (KPs). In this paper, we present the design of the Explanatory Agent (xARA), a case-based ARA that answers biomedical queries by accessing multiple KPs, ranking results, and explaining the ranking of results. The Explanatory Agent is designed with five knowledge containers that include the four original knowledge containers and one additional container for explanation - the Explanation Container. The Explanation Container is case-based and designed with its own knowledge containers.