[9p-Z09-1~18] 23.1 Joint Session N "Informatics"

▲ [9p-Z09-15] Supercuration: A machine-assisted data curation tool for rapid database construction for materials informatics

〇Luca Foppiano¹, Masashi Ishii¹ (1.Material Database Group, MaDIS, NIMS)

Keywords:text mining, materials informatics, superconductors

The establishment of Text and Data Mining (TDM) processes is required by Materials Informatics (MI) to accelerate toward data-driven material discovery. Although a lot of effort has been made for this establishment, full automatic TDM processes are still challenging. The National Institute for Materials Science (NIMS) is constructing several databases for MI, and SuperCon is a hopeful data source in superconductor domain. While we are implementing an automatic TDM system for extracting materials and related properties from scientific literature, we developed Supercuration. A machine-assisted curation tool for accelerating the manual data process in SuperCon. Supercuration interfaces with the automatic TDM system and allows users to visualise and correct the extracted data from a document. Output data (materials - properties) are aggregated as an editable table and the originally extracted entities are visualised as markers on a layer on top of the original documents.