Skip to main content
. 2024 Mar 14;24:75. doi: 10.1186/s12911-024-02481-8

Table 7.

Automatic evaluation metrics for BERTSUM, BART, and ChatGPT summaries, such as comparisons of ROUGE-1, ROUGE-2, ROUGE-L and BERTScore scores

Model ROUGE-1 ROUGE-2 ROUGE-L BERTScore
BERTSUM_Classifier 34.51 13.94 24.47 63.53
BERTSUM_Transfromer 33.52 13.21 24.06 63.21
BERTSUM_RNN 33.73 13.62 24.17 63.18
BART 55.39 40.38 54.21 78.32
ChatGPT(Prompt_T.7) 48.19 25.41 40.81 73.38