Update README.md

README.md

@@ -27,7 +27,7 @@ comparable to those of human annotators.
 
 The fine-tuned ParlaCAP model achieves 0.723 in macro-F1 on an English test set, 
 0.686 in macro-F1 on a Croatian test set, 0.710 in macro-F1 on a Serbian test set and 0.646 in macro-F1 on a Bosnian test set
-(app. 880 instances from ParlaMint-GB 4.1, ParlaMint-HR 4.1, ParlaMint-RS 4.1 and ParlaMint-BA 4.1, respectively, balanced by labels).
+(app. 880 manually-annotated instances from ParlaMint-GB 4.1, ParlaMint-HR 4.1, ParlaMint-RS 4.1 and ParlaMint-BA 4.1, respectively, balanced by labels).
 
 For end use scenarios, we recommend filtering out predictions based on the model's prediction confidence.