You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Go to file

Kai Labusch dbe8d1c1e4 change to more recent dask and pyarrow version		5 years ago
qurator	re-structure repo	5 years ago
Dockerfile	re-structure repo	5 years ago
Dockerfile.cpu	re-structure repo	5 years ago
LICENSE	re-structure repo	5 years ago
README.md	re-structure repo	5 years ago
requirements.txt	change to more recent dask and pyarrow version	5 years ago
setup.py	re-structure repo	5 years ago

README.md

Preprocessing of NER ground-truth:

compile_conll

Read CONLL 2003 ner ground truth files from directory and write the outcome of the data parsing to some pandas DataFrame that is stored as pickle.

Usage

compile_conll --help

compile_germ_eval

Read germ eval .tsv files from directory and write the outcome of the data parsing to some pandas DataFrame that is stored as pickle.

Usage

compile_germ_eval --help

compile_europeana_historic

Read europeana historic ner ground truth .bio files from directory and write the outcome of the data parsing to some pandas DataFrame that is stored as pickle.

Usage

compile_europeana_historic --help

compile_wikiner

Read wikiner files from directory and write the outcome of the data parsing to some pandas DataFrame that is stored as pickle.

Usage

compile_wikiner --help

Train BERT - NER model:

bert-ner

Perform BERT for NER supervised training and test/cross-validation.

Usage

bert-ner --help