Towards a scientific workflow featuring Natural Language Processing for the digitisation of natural history collections

In this article, the authors explore the feasibility of using natural language processing (NLP) on top of optical character recognition (OCR) to assist the transcription of label information from natural history collections.

Additional Info

Field Value
URL https://riojournal.com/article/58030/
Task Clusters Digital Data Capture
Preparations General
Discipline General
Audience
  • Collections Professionals
  • Participatory Sciences Project Coordinators
Language English
Category Journal Article
DOI https://doi.org/10.3897/rio.6.e58030
First Author David Owen
Other Authors
  1. Quentin Groom
  2. Alex Hardisty
  3. Thijs Leegwater
  4. Laurence Livermore
  5. Myriam van Walsum
  6. Noortje Wijkamp
  7. Irena Spasić
Publisher Research Ideas and Outcomes
Volume Number 6
Pagination e58030
Date Published 2020-08-28
Version v2
Accessible for Free Yes

Other versions

This dataset has no data