Discourse

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Knowledge Base2 results

Text SummarizationonArxiv HEP-TH citation graph
ROUGE-1· 2018-04-16
35.8
best: 50.95 (Top Down Transformer (AdaPool) (464M))
SOTA
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents arXiv:1804.05685
Text SummarizationonPubmed
ROUGE-1· 2018-04-16
38.93
best: 51.05 (Top Down Transformer (AdaPool) (464M))
SOTA
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents arXiv:1804.05685