University of Illinois Urbana-Champaign

Name Matters: Taxonomic Name Recognition (TNR) in Biodiversity Heritage Library (BHL)

Wei, Qin; Heidorn, P. Bryan; Freeland, Chris

Permalink

https://hdl.handle.net/2142/14919

Description

Title
Name Matters: Taxonomic Name Recognition (TNR) in Biodiversity Heritage Library (BHL)
Author(s)
  • Wei, Qin
  • Heidorn, P. Bryan
  • Freeland, Chris
Issue Date
2010-02-03
Keyword(s)
  • Taxonomic Name Recognition
  • TNR
  • biodiversity informatics
  • Machine Learning
  • Digital Libraries
  • Information Retrieval
Abstract
Taxonomic Name Recognition is prerequisite for more advanced processing and mining of full-text taxonomic literatures. This paper investigates three issues of current TNR tools in detail: (1) The difficulties and methods used in TNRs. (2) The performance of Optical Character Recognition (OCR) and TNR tools by samples from Biodiversity Heritage Library (BHL). (3) The methods for potential improvement. We found that the performances of current TNR techniques need to be improved. A detailed error analysis reveals that sublanguage characteristics account for much of the error. A preliminary experiment using NaiveBayes (NB) models shows the potential of using machine learning (ML) in TNR.
Type of Resource
text
Permalink
http://hdl.handle.net/2142/14919

Owning Collections

iConference 2010 Papers PRIMARY
Conference Papers