Lodoss-full-base (extractive)

Reported on 6 benchmarks across 1 task · 1 paper

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

Knowledge Base6 results

Text SummarizationonArxiv HEP-TH citation graph
ROUGE-1· 2022-10-28
48.2
best: 50.95 (Top Down Transformer (AdaPool) (464M))
Toward Unifying Text Segmentation and Long Document Summarization arXiv:2210.16422
Text SummarizationonArxiv HEP-TH citation graph
ROUGE-2· 2022-10-28
20.5
best: 21.93 (Top Down Transformer (AdaPool) (464M))
Toward Unifying Text Segmentation and Long Document Summarization arXiv:2210.16422
Text SummarizationonArxiv HEP-TH citation graph
ROUGE-L· 2022-10-28
42.28
best: 45.61 (Top Down Transformer (AdaPool) (464M))
Toward Unifying Text Segmentation and Long Document Summarization arXiv:2210.16422
Text SummarizationonPubmed
ROUGE-1· 2022-10-28
48.93
best: 51.05 (Top Down Transformer (AdaPool) (464M))
Toward Unifying Text Segmentation and Long Document Summarization arXiv:2210.16422
Text SummarizationonPubmed
ROUGE-2· 2022-10-28
23.51
best: 24.76 (LongT5)
Toward Unifying Text Segmentation and Long Document Summarization arXiv:2210.16422
Text SummarizationonPubmed
ROUGE-L· 2022-10-28
44.4
best: 46.67 (LongT5)
Toward Unifying Text Segmentation and Long Document Summarization arXiv:2210.16422