Hierarchical Learning for Generation with Long Source Sequences

Benchmark Model Rank Results
document-summarization-on-cnn-daily-mailHAT-BARTROUGE-1: 44.48ROUGE-2: 21.31ROUGE-L: 41.52
reading-comprehension-on-raceHAT (Encoder)Accuracy: 67.3
text-summarization-on-arxivHAT-BARTROUGE-1: 46.74ROUGE-2: 19.19ROUGE-L: 42.2
text-summarization-on-pubmed-1HAT-BARTROUGE-1: 48.25ROUGE-2: 21.35ROUGE-L: 36.69
text-summarization-on-samsum-corpusHAT-CNNDMROUGE-1: 53.01ROUGE-2: 28.27
text-summarization-on-samsum-corpusHAT-CNNDM RLROUGE-L: 48.84
text-summarization-on-x-sumHAT-BARTROUGE-1: 45.92ROUGE-2: 22.79