JaMIE: A Pipeline Japanese Medical Information Extraction System
This work addresses medical information extraction for Japanese healthcare, but it is incremental as it applies existing methods to a new language and domain.
The authors tackled medical information extraction from Japanese reports by proposing a new relation annotation schema and a pipeline system, achieving accurate performance with empirical results highlighting effective annotation strategies and the superiority of contextual embedding models.
We present an open-access natural language processing toolkit for Japanese medical information extraction. We first propose a novel relation annotation schema for investigating the medical and temporal relations between medical entities in Japanese medical reports. We experiment with the practical annotation scenarios by separately annotating two different types of reports. We design a pipeline system with three components for recognizing medical entities, classifying entity modalities, and extracting relations. The empirical results show accurate analyzing performance and suggest the satisfactory annotation quality, the effective annotation strategy for targeting report types, and the superiority of the latest contextual embedding models.