Tool stats & trends
Looking to identify usage trends or leading experts?
|Restrictions to use||None|
- person_outline Andreas Kurtz
Publication for CellFinder
Deep learning with word embeddings improves biomedical named entity recognition
[…] t make the LSTM-CRF method reach a precision higher than that of the CRF method. We inspected these evaluations in more detail. The lower precision values on average are mostly due to the two corpora CellFinder and Variome. However, both corpora miss some of the species annotations. For instance, the 41 FP predictions of LSTM-CRF for Variome are 21 times the term ‘mouse’, 4 times ‘mice’ and 16 tim […]
BioC interoperability track overview
[…] include genes, mutations, chemicals, protein–protein interactions, disease–treatment relations and gene expression and phosphorylation events. Brat2BioC was also used to make the Human Variome () and CellFinder () corpora available in BioC.The NCBI disease corpus of hand-annotated disease names is now available in the BioC format (). In addition, it was processed by the C++ and Java pipelines, so […]
An analysis on the entity annotations in biological corpora
[…] A families or groups, proteins, protein complexes and protein families and groups. Just as the other five PPI corpora, the BioInfer corpus has been used for training and evaluation of several tools . CellFinder. The CellFinder corpus was developed in the scope of the CellFinder database ( http://cellfinder.de/) and includes annotations for six entity types (anatomical parts, cell lines, cell type […]
Preliminary evaluation of the CellFinder literature curation pipeline for gene expression in kidney cells and anatomical parts
[…] No, this is not a gene.  No, this is not a cell or anatomical part.  No, both gene and cell or anatomical part are incorrect.  No, the snippet (publication) does not seem to be relevant for CellFinder. Figure 3. […]
Looking to check out a full list of citations?
Be the first to review CellFinder