List your company

Abstractive Summarization on CNNDM (test)

47.78ROUGE-1BRIO-Mul
44.015244.992645.9746.9474Mar 31, 2022

Evaluation results

MethodLinks
BRIO-MulBackbone=BART, Training Loss=Multi-task Loss, Training Mode=Fine-tuned2022.0347.7823.5544.57
BRIO-CtrBackbone=BART, Training Loss=Contrastive Loss Only, Training Mode=Fine-tuned2022.0347.2822.9344.15
SimCLSBackbone=BART, Evaluation Model=RoBERTa, Evaluation Source=Original Paper2022.0346.6722.1543.54
GSumBackbone=BART, Evaluation Source=Original Paper2022.0345.9422.3242.48
GOLD-pBackbone=BART, Evaluation Source=Original Paper2022.0345.422.0142.25
SeqCoBackbone=BART, Evaluation Source=Original Paper2022.0345.0221.841.75
GOLD-sBackbone=BART, Evaluation Source=Original Paper2022.0344.8222.0941.81
ConSumBackbone=BART, Evaluation Source=Original Paper2022.0344.5321.5441.57
BARTBackbone=BART, Evaluation Source=Current Paper Evaluation Script2022.0344.2921.1741.09
PEGASUSEvaluation Source=Original Paper2022.0344.1721.4741.11
BARTBackbone=BART, Evaluation Source=Original Paper2022.0344.1621.2840.9