Automatic Metrics

Two readability indices were used to perform automatic evaluations of the generated text, namely, FKGL and Automatic Readability Indices (ARIs). The SARI score is a standard metric for TS. The F-1 versions of ROUGE-1 and ROUGE-2 [44] scores were also reported. Readers can find more details about these metrics in Multimedia Appendix 2. To measure the quality of the generated text, the criteria proposed by Yuan et al [45] were used, which are mentioned in the “Automatic Evaluation Metrics” section in Multimedia Appendix 2. The criteria proposed by Yuan et al [45] can be automatically computed using a language model–based metric called “BARTScore.” Further details on how to use BARTScore to measure the quality of the generated text are also mentioned in Multimedia Appendix 2.