Text Summarization On Pubmed 1

Metrics

ROUGE-1

ROUGE-2

ROUGE-L

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	ROUGE-1	ROUGE-2	ROUGE-L
gosum-extractive-summarization-of-long	49.83	23.56	45.10
longt5-efficient-text-to-text-transformer-for	50.23	24.76	46.67
extractive-summarization-as-text-matching	41.21	14.91	36.75
pegasus-pre-training-with-extracted-gap	45.09	-	-
on-extractive-and-abstractive-neural-document	45.01	-	-
a-discourse-aware-attention-model-for	38.93	-	-
a-divide-and-conquer-approach-to-the	43.98	17.65	40.25
adapting-pretrained-text-to-text-models-for	50.3	-	-
toward-unifying-text-segmentation-and-long	49.38	23.89	44.84
systematically-exploring-redundancy-reduction	45.39	20.37	40.99
systematically-exploring-redundancy-reduction	45.3	20.42	40.95
hierarchical-learning-for-generation-with	48.25	21.35	36.69
big-bird-transformers-for-longer-sequences	46.32	20.65	42.33
a-divide-and-conquer-approach-to-the	46.34	19.97	42.42
fastformer-additive-attention-is-all-you-need	38.09	15.44	34.81
gretel-graph-contrastive-topic-enhanced	48.20	21.20	43.16
extractive-summarization-of-long-documents-by	44.81	19.74	-
long-document-summarization-with-top-down-and-1	51.05	23.26	46.47
a-divide-and-conquer-approach-to-the	44.09	17.69	40.27
scaling-up-summarization-leveraging-large	50.34	24.57	45.96
on-extractive-and-abstractive-neural-document	43.3	-	-
histruct-improving-extractive-text-1	46.59	20.39	42.11
factorizing-content-and-budget-decisions-in	47.5	20.33	43.76
memsum-extractive-summarization-of-long	49.25	22.94	44.42
on-extractive-and-abstractive-neural-document	41.43	-	-
sparsifying-transformer-models-with	47.81	21.14	-
gencomparesum-a-hybrid-unsupervised	42.10	16.51	38.25
get-to-the-point-summarization-with-pointer	35.86	-	-
toward-unifying-text-segmentation-and-long	48.93	23.51	44.40