Assessing the impact of OCR quality on downstream NLP tasks

Conference Object
Change log

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.

Optical Character Recognition, OCR, Digital Humanities, Natural Language Processing, NLP, Information Retrieval
Journal Title
ICAART 2020 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence
Conference Name
Special Session on Artificial Intelligence and Digital Heritage: Challenges and Opportunities
Journal ISSN
Volume Title
SCITEPRESS - Science and Technology Publications
All rights reserved
Alan Turing Institute (EP/N510129/1)
AHRC (via Alan Turing Institute) (Unknown)