Table 6:

Word Classification: the best model for word classification for each approach: (1) ALL CATEGORIES BINARY: binary classification ignorance or not, (2) AN ENSEMBLE OF BINARY CLASSIFIERS: binary classification for each class (reported) combined to create the ensemble, and (3) ALL CATEGORIES COMBINED: one multi-classifier to all categories.

Ignorance Category	Model	testing F1 score	testing support
ALL CATEGORIES BINARY	BioBERT	0.89	7601
answered question	BioBERT	0.89	320
unknown/novel	CRF	0.98	155
explicit inquiry	BioBERT	0.97	43
incompletely understood	BioBERT	0.93	2809
indefinite relationship	BioBERT	0.97	1205
largely understood	BioBERT	0.94	618
anomalous/curious	BioBERT	0.96	399
alternative/controversy	BioBERT	0.91	598
difficult	CRF	0.93	128
problem/complication	BioBERT	0.9	238
future work	BioBERT	0.89	391
future prediction	BioBERT	0.94	100
important consideration	BioBERT	0.93	608
ALL CATEGORIES COMBINED*	BioBERT	0.82	6239

^*Reporting the average F1 score of all the categories for one multi-classifier.