A machine learning software for extracting information from scholarly documents
Changes:
transparent usage of DeLFT deep learning models (usual BidLSTM-CRF) instead of Wapiti CRF models, native integration via JEP
support of biblio-glutton as DOI/metadata matching service, alternative to crossref REST API
improvement of citation context identification and matching (+9% recall with similar precision, for PMC sample 1943 articles, from 43.35 correct citation contexts per article to 49.98 correct citation contexts per article)
citation callout now in abstract, figure and table captions
structured abstract (including update of TEI schema)
bug fixes and some more parameters: by default using all available threads when training and possibility to load models at the start of the service
Changes:
Changes:
http://localhost:8071
)Bug fixes
The latest stable release of GROBID is version 0.5.0
. As compared to previous version 0.4.3
, this version brings:
Fixed issue that was making the release build not working
The latest stable release of GROBID is version 0.4.3. As compared to previous version 0.4.2, this version brings:
Versions 0.4.2 of GROBID
Latest stable version for versions 0.3.* of GROBID