MagneticMaterials.org makes use of the ChemDataExtractor toolkit to automatically extract magnetic and superconductivity property information from scientific articles and compile this information into auto-generated materials databases.
For a guide on the ChemDataExtractor toolkit please see the docs, available at ChemDataExtractor.org
The adapted toolkit now makes use of semi-supervised machine learning to extract Curie and Néel phase transition relationships in a probabilistics manner. Based on the Snowball relationship extraction algorithm, this method helps the system to continually learn new relationships as it sees more examples.
The following pages demonstrate how to install, train and use the toolkit to generate a database of Néel temperatures.
If you use ChemDataExtractor with Snowball as a resource in your research, please cite the following works:
Swain, M. C., & Cole, J. M. "ChemDataExtractor: A Toolkit for Automated Extraction of Chemical Information from the Scientific Literature", J. Chem. Inf. Model. 2016, 56 (10), pp 1894–1904 10.1021/acs.jcim.6b00207
Court, C. J. & Cole, J. M. "Autogenerated materials database of Curie and Néel temperatures via semi-supervised relationship extraction", Scientific Data. 2018, 5, Article number: 180111 10.1038/sdata.2018.111