Repository logo
Home
Research Outputs
Collections
Statistics
Shared Repository Homepage
  1. Home
  2. Cultural Heritage Shared Repository Service
  3. British Library
  4. Conference Item
  5. Assessing the Impact of OCR Quality on Downstream NLP Tasks

Assessing the Impact of OCR Quality on Downstream NLP Tasks

Thumbnail Image
Download
Name

ARTIDIGH_2020_7_CR.pdf

Description
visibility:open
Size

2.05 MB

Format

Adobe PDF

Checksum (CRC64NVME)

bEwQniIRscE=

Resource type
Conference paper (unpublished)
Creator (person)
van Strien, Daniel
ORCIDORCID logo
Beelen, Kaspar
ORCIDORCID logo
Coll Ardanuy, Mariona
ORCIDORCID logo
Hosseini, Kasra
ORCIDORCID logo
McGillivray, Barbara
ORCIDORCID logo
Colavizza, Giovanni
ORCIDORCID logo
Date published
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.
Contributor (organisation)
British Library
Living with Machines
Project(s)
Living with Machines
Funder
Funder nameAwards
Arts and Humanities Research Council
AH/S01179X/1
Event title
ICAART 2020: 12th International Conference on Agents and Artificial Intelligence
Related URL
http://www.insticc.org/node/TechnicalProgram/icaart/presentations
Keywords
information retrieval
Natural Language Processing
OCR
NLP
digital humanities
Optical Character Recognition
Collection
Living with Machines
Managed by the British Library and supported by the AHRC

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Cookie settings
  • End User Agreement
  • About
  • Contact
  • Help
Repository logo COAR Notify