Skip to content

Latest commit

 

History

History
26 lines (18 loc) · 965 Bytes

README.md

File metadata and controls

26 lines (18 loc) · 965 Bytes

vernacular-names-extraction

Code and resources for automatic extraction of vernacular name-related information in triple structure from botanical works, i.e. Bosshard (1978).

resources:

Bosshard, Hans Heinrich (1978): Mundartnamen von Bäumen und Sträuchern in der deutschsprachigen Schweizund im Fürstentum Liechtenstein. Bühler Druck AG, Zürich.
https://zenodo.org/record/293746/files/bosshard_1978_OCRr.pdf

motivation:

Google search for the Swiss German vernacular name “wysshulftere” (Viburnum opulus) re-directs to digitized, OCRed work from Bosshard.

goal:

add information related to vernacular names to open-source knowledge bases.

task:

extract the following information:

  • venacular names,
  • associated scientific (Latin) name,
  • standard German book name ('Buchname'),
  • geographic location where plant occurs,
  • authorship information

output format:

information triples in a .tsv file