#Geoparsing is about identifying and locating place references in texts. Does it matter which language is being geoparsed? In a new @ijgis article, we examine that question through building a geoparser for the morphologically complex Finnish. Co-authored with my wonderful supervisors @tuuli & @tuomo
The article: https://doi.org/10.1080/13658816.2024.2369539
Gotta give it up to the wicked smart @tadusko on his fresh article on #geoparsing out now on #IJGIS. Not only is it a highly interesting piece on how to make geoparsing better overall and specifically for morphologically complex languages like Finnish, but it is also well-written. A pleasure to read overall.
Check it out here https://doi.org/10.1080/13658816.2024.2369539
How can we find and locate place names from texts? How can we do it for Finnish?
Results from my #PhD and the @digigeolab #MOBICON project are starting to trickle out! A paper out soon, but the OS #Python tool for Finnish "geoparsing" is available here https://github.com/Tadusko/fi-geoparser
Now to the fun part: writing documentation...
Next: Harri Kiiskinen, Asko Nivala, Jasmine Westerlund, and Juhana Saarelainen (2023). “Extracting Geographical References from Finnish Literature. Fully Automated Processing of Plain-Text Corpora”. In: Journal of Computational Literary Studies 2 (1). doi: https://doi.org/10.48694/jcls.3584.
Keywords: named entity recognition, geographic information system, #geoparsing linked open data, literary geography, #Finland
Day 30 - "My favorite... lyricist!"
The beloved Finnish singer-songwriter Juice Leskinen takes us on a world-tour with words. We mapped the geography of Juice by locating the place names in his lyrics with #geoparsing.
By: @tadusko and @matabatchi
