@inproceedings{mieskes-schmunk-2019-ocr,
    title = "{OCR} Quality and {NLP} Preprocessing",
    author = "Mieskes, Margot  and
      Schmunk, Stefan",
    editor = "Axelrod, Amittai  and
      Yang, Diyi  and
      Cunha, Rossana  and
      Shaikh, Samira  and
      Waseem, Zeerak",
    booktitle = "Proceedings of the 2019 Workshop on Widening NLP",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-3633/",
    pages = "102--105",
    abstract = "We present initial experiments to evaluate the performance of tasks such as Part of Speech Tagging on data corrupted by Optical Character Recognition (OCR). Our results, based on English and German data, using artificial experiments as well as initial real OCRed data indicate that already a small drop in OCR quality considerably increases the error rates, which would have a significant impact on subsequent processing steps."
}