The goal of this GROBID module is to identify, extract and link entities in text from
superconductors-related scientific literature.
In particular, the goal is to extract superconductor materials and their related
properties, such a Critical Temperature (Tc), Critical pressure, measurement methods.
As the others GROBID models, grobid-supercondcutors relies on machine learning and
can use linear CRF (via Wapiti JNI integration) or
Deep Learning model such as BiLSTM-CRF with or without ELMo (via DeLFT JNI integration).
The linking is implemented as Python library in a separate project grobid-superconductors-tools
(private), which contains also other utilities.
The project is available on Github.
References
This project was described in the following papers:
- "Automatic extraction of materials and properties from superconductors scientific literature": PDF
- "SuperMat: construction of a linked annotated dataset from superconductors-related publications": PDF
- "Proposal for Automatic Extraction of Superconductors properties from scientific literature": PDF
Acknowledgement
Our warmest thanks to @kermitt2(Science-miner): Author of Grobid, Delft and tons of other interesting open source projects.
This project has been developed at the National Institute for Materials Science, in Tsukuba, Japan.
License
GROBID and grobid-superconductors are distributed under Apache 2.0
license.
Contact: Luca Foppiano (luca AT foppiano.org)