Skip to main content

Table 4 Results over LMs finetuned by open-domain reading comprehension dataset without KBs on the CDR dataset

From: Biomedical relation extraction via knowledge-enhanced reading comprehension

Model Intra sentential level Inter sentential level Document level
P (%) R (%) F1 (%) P (%) R (%) F1 (%) P (%) R (%) F1 (%)
biobert 62.27 57.13 59.59 49.80 11.44 18.61 59.85 69.23 64.20
biobert+SQuAD 67.09 54.50 60.14 60.10 11.16 18.83 65.83 66.32 66.07