Table 2.

ROUGE-1, ROUGE-2, and SARI scores for the generated text.^a

Model	ROUGE-1	ROUGE-2	SARI
BART-Fine-tuned	0.40	0.11	0.39
BART-UL	0.38	0.14	0.40b
TESLEA	0.39	0.11	0.40b
MUSSc	0.23	0.03	0.34
Keep it Simple	0.23	0.03	0.32
PEGASUS-large	0.44b	0.18b	0.40b
PEGASUS-pubmed-large	0.42	0.16	0.40b

^aTESLEA achieves similar performance to other models. Higher scores of ROUGE-1, ROUGE-2, and SARI are desirable.

^bBest performance.

^cMUSS: multilingual unsupervised sentence simplification.