Text Summarization on CNN / Daily Mail (Anonymized)

Metric: ROUGE-L (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	ROUGE-L▼	Extra Data	Paper	Date↕	Code
1	RNES w/o coherence	37.75	No	Learning to Extract Coherent Summary via Deep Re...	2018-04-19	-
2	SWAP-NET	37.7	No	-	-	Code
3	HSSAS	37.6	No	A Hierarchical Structured Self-Attentive Model f...	2018-05-20	-
4	ML+RL ROUGE+Novel, with LM	37.44	No	Improving Abstraction in Text Summarization	2018-08-23	-
5	rnn-ext + abs + RL + rerank	37.34	No	Fast Abstractive Summarization with Reinforce-Se...	2018-05-28	Code
6	ML+RL, with intra-attention	36.9	No	A Deep Reinforced Model for Abstractive Summariz...	2017-05-11	Code
7	GAN	36.71	No	Generative Adversarial Network for Abstractive T...	2017-11-26	Code
8	Fastformer	36.21	No	Fastformer: Additive Attention Can Be All You Need	2021-08-20	Code
9	KIGN+Prediction-guide	35.68	No	-	-	-
10	Lead-3 baseline	35.5	No	SummaRuNNer: A Recurrent Neural Network based Se...	2016-11-14	Code
11	SummaRuNNer	35.3	No	SummaRuNNer: A Recurrent Neural Network based Se...	2016-11-14	Code
12	Tan et al.	34	No	-	-	-
13	words-lvt2k-temp-att	32.65	No	Abstractive Text Summarization Using Sequence-to...	2016-02-19	Code

#1RNES w/o coherenceSOTA
37.75
ROUGE-L· 2018-04-19
Learning to Extract Coherent Summary via Deep Reinforcement Learning
#2SWAP-NET
37.7
ROUGE-L
No paperCode
#3HSSAS
37.6
ROUGE-L· 2018-05-20
A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)
#4ML+RL ROUGE+Novel, with LM
37.44
ROUGE-L· 2018-08-23
Improving Abstraction in Text Summarization
#5rnn-ext + abs + RL + rerank
37.34
ROUGE-L· 2018-05-28
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting Code
#6ML+RL, with intra-attentionSOTA
36.9
ROUGE-L· 2017-05-11
A Deep Reinforced Model for Abstractive Summarization Code
#7GAN
36.71
ROUGE-L· 2017-11-26
Generative Adversarial Network for Abstractive Text Summarization Code
#8Fastformer
36.21
ROUGE-L· 2021-08-20
Fastformer: Additive Attention Can Be All You Need Code
#9KIGN+Prediction-guide
35.68
ROUGE-L
No paper
#10Lead-3 baselineSOTA
35.5
ROUGE-L· 2016-11-14
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents Code
#11SummaRuNNer
35.3
ROUGE-L· 2016-11-14
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents Code
#12Tan et al.
34
ROUGE-L
No paper
#13words-lvt2k-temp-attSOTA
32.65
ROUGE-L· 2016-02-19
Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond Code