Transformers-sklearn: a toolkit for medical language understanding with transformer-based models

Table 6 The experimental results of transformers-sklearn and transformers in four medical NLP tasks (mode_type = “roberta”)

Name	Score		Second		Lines of code		Pre-trained model
Name	Ours	Transformers	Ours	Transformers	Ours	Transformers	Pre-trained model
TrialClassification	0.8148^a	0.8231^a	1206	1208	38	246	chinese-roberta-wwm-ext
BC5CDR	0.8528^a	0.8461^a	460	504	41	309	roberta-base
DiabetesNER	0.7068^a	0.7184^a	1445	1426	63	309	chinese-roberta-wwm-ext
BIOSSES	0.3996^b	0.3614^b	36	17	41	246	roberta-base

^aThe value of Macro F1, where the bolded one indicates the best performance
^bThe value of Person correlation, where the bolded one indicates the best performance

ISSN: 1472-6947