This repository hosts several scripts that are taken from programming projects.
imgtopdf_handler.py takes an image file, transforms it to a pdf and adds an ocr layer.
Deployed in the context of a flask app. (04/2021)
run_ner_crossval.py evokes a pre-trained BERT model to run token classification on input data, includes cross-validation for hyperparameter selection.
Used in the master's thesis. (11/2020)
ElasticWriter.java writes UIMA CAS files into an Elasticsearch database.
Deployed in a Textmining Toolbox at IAIS. (07/2020)
For questions or remarks please contact the holder of this repository.