History

Nathan TeBlunthuis 282208507a Keep better track of time. - Add timestamp ot transliterations output file. - Append wikidata search terms instead of overwriting		2020-03-28 13:52:54 -07:00
..
analysis	typo fix	2020-03-28 10:01:43 -07:00
data	add output files from tranliteration search using google trends	2020-03-27 16:53:03 -07:00
src	Keep better track of time.	2020-03-28 13:52:54 -07:00
README.md	Finish MVP for transliterations	2020-03-24 22:06:45 -07:00
requirements.txt	add mwapi to requirements	2020-03-27 20:05:07 -07:00

README.md

Transliterations

This part of the project collects tranliterations of key phrases related to COVID-19 using Wikidata. We search the Wikidata API for entities in src/wikidata_search.py and then we make simple SPARQL queries in src/wikidata_transliterations.py to collect labels and aliases the entities. The labels come with language metadata. This seems to provide a decent initial list of relevant terms across multiple languages.