Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization

Open paper
Benchmark Model Rank Results
text-summarization-on-dialogsumSICK#2Rouge1: 46.26Rouge2: 20.95RougeL: 41.05BertScore: 71.30
text-summarization-on-samsum-corpusSICK#3ROUGE-1: 53.73ROUGE-2: 28.81ROUGE-L: 49.5BertScoreF1: 71.92

Rank counts only results with a code link.