Assessing the Impact of OCR Quality on Downstream NLP Tasks

Daniel van Strien, Kaspar Beelen, Mariona Ardanuy, Kasra Hosseini, Barbara McGillivray, Barbara McGillivray, Giovanni Colavizza, Giovanni Colavizza

2020

Abstract

A growing volume of heritage data is being digitized and made available as text via optical character recognition (OCR). Scholars and libraries are increasingly using OCR-generated text for retrieval and analysis. However, the process of creating text through OCR introduces varying degrees of error to the text. The impact of these errors on natural language processing (NLP) tasks has only been partially studied. We perform a series of extrinsic assessment tasks — sentence segmentation, named entity recognition, dependency parsing, information retrieval, topic modelling and neural language model fine-tuning — using popular, out-of-the-box tools in order to quantify the impact of OCR quality on these tasks. We find a consistent impact resulting from OCR errors on our downstream tasks with some tasks more irredeemably harmed by OCR errors. Based on these results, we offer some preliminary guidelines for working with text produced through OCR.

Paper Citation

in Harvard Style

van Strien D., Beelen K., Ardanuy M., Hosseini K., McGillivray B. and Colavizza G. (2020). Assessing the Impact of OCR Quality on Downstream NLP Tasks. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ARTIDIGH, ISBN 978-989-758-395-7, pages 484-496. DOI: 10.5220/0009169004840496

in Bibtex Style

@conference{artidigh20,
author={Daniel van Strien and Kaspar Beelen and Mariona Ardanuy and Kasra Hosseini and Barbara McGillivray and Giovanni Colavizza},
title={Assessing the Impact of OCR Quality on Downstream NLP Tasks},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ARTIDIGH,},
year={2020},
pages={484-496},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009169004840496},
isbn={978-989-758-395-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ARTIDIGH,
TI - Assessing the Impact of OCR Quality on Downstream NLP Tasks
SN - 978-989-758-395-7
AU - van Strien D.
AU - Beelen K.
AU - Ardanuy M.
AU - Hosseini K.
AU - McGillivray B.
AU - Colavizza G.
PY - 2020
SP - 484
EP - 496
DO - 10.5220/0009169004840496