SummaRuNNer

Reported on 3 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 Base3 results

Text SummarizationonCNN / Daily Mail (Anonymized)
ROUGE-1· 2016-11-14
39.6
best: 42.3 (HSSAS)
SOTA
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents arXiv:1611.04230
Text SummarizationonCNN / Daily Mail (Anonymized)
ROUGE-2· 2016-11-14
16.2
best: 18.87 (RNES w/o coherence)
SOTA
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents arXiv:1611.04230
Text SummarizationonCNN / Daily Mail (Anonymized)
ROUGE-L· 2016-11-14
35.3
best: 37.75 (RNES w/o coherence)
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents arXiv:1611.04230