Emmanueldave/nulis baseline update

IndoNLP / nusa-writes

NusaWrites is an in-depth analysis of corpora collection strategy and a comprehensive language modeling benchmark for underrepresented and extremely low-resource Indonesian local languages.

Apache License 2.0

24 stars 2 forks source link

Emmanueldave/nulis baseline update #7

Closed emmanueldavee closed 1 year ago

emmanueldavee commented 1 year ago

Add new langage dataset (already split)
Add export weighted F1 from classification report (in case needed for further analysis)
Refactor text_column_name and label_column_name as argument to handle different column names like in the author dataset