TLM-I+E

Reported on 2 benchmarks across 1 task · 1 paper · 1 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· 2019-09-07
42.43
best: 50.95 (Top Down Transformer (AdaPool) (464M))
SOTA
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models arXiv:1909.03186
Text SummarizationonPubmed
ROUGE-1· 2019-09-07
41.43
best: 51.05 (Top Down Transformer (AdaPool) (464M))
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models arXiv:1909.03186