Data Centric Domain Adaptation for Historical Text with OCR Errors

Resources:

• Preprint
• Preprocessed Europeana NER Data on GitHub

Contact:

• Luisa März
• Stefan Schweter

If you use the approach or data in your work, please cite the following paper (to appear at ICDAR 2021):

@article{2107.00927v1,
  author = {März, Luisa and Schweter, Stefan and Poerner, Nina and Roth, Benjamin and Schütze, Hinrich},
  eprint = {2107.00927},
  journal = {arXiv:2107.00927},
  month = {Jul},
  title = {{Data Centric Domain Adaptation for Historical Text with OCR Errors}},
  type = {article},
  url = {http://arxiv.org/abs/2107.00927},
  year = {2021},
}