PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation

Open paper
Benchmark Model Rank Results
abstractive-text-summarization-on-cnn-dailyPALM#15ROUGE-1: 44.30ROUGE-2: 21.12ROUGE-L: 41.41
text-summarization-on-gigawordPALM#8ROUGE-1: 39.45ROUGE-2: 20.37ROUGE-L: 36.75

Rank counts only results with a code link.