Wikidata / StrepHit

An intelligent reading agent that understands text and translates it into Wikidata statements.
https://meta.wikimedia.org/wiki/Grants:IEG/StrepHit:_Wikidata_Statements_Validation_via_References
GNU General Public License v3.0
112 stars 14 forks source link

Plug in a gazetteer as extra features for the classifier #38

Closed marfox closed 8 years ago

marfox commented 8 years ago

The supervised classifier should be able to read a gazetteer from a file. The format is JSONlines, where key = human-readable feature label, and value = list of relevant n-grams. For instance, ARTIST: [picasso, michelangelo merisi, vincent van gogh]