Document Summarization on CNN / Daily Mail

Metric: ROUGE-1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	ROUGE-1▼	Extra Data	Paper	Date↕	Code
1	Scrambled code + broken (alter)	48.18	No	Universal Evasion Attacks on Summarization Scoring	2022-10-25	Code
2	PEGASUS + SummaReranker	47.16	No	SummaReranker: A Multi-Task Mixture-of-Experts R...	2022-03-13	Code
3	Fourier Transformer	44.76	No	Fourier Transformer: Fast Long Range Modeling by...	2023-05-24	Code
4	GLM-XXLarge	44.7	No	GLM: General Language Model Pretraining with Aut...	2021-03-18	Code
5	HAT-BART	44.48	No	Hierarchical Learning for Generation with Long S...	2021-04-15	-
6	MatchSum (RoBERTa-base)	44.41	No	Extractive Summarization as Text Matching	2020-04-19	Code
7	Hie-BART	44.35	No	-	-	-
8	MatchSum (BERT-base)	44.22	No	Extractive Summarization as Text Matching	2020-04-19	Code
9	BertSumExt	43.85	Yes	Text Summarization with Pretrained Encoders	2019-08-22	Code
10	BigBird-Pegasus	43.84	No	Big Bird: Transformers for Longer Sequences	2020-07-28	Code
11	T5-11B	43.52	Yes	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
12	BERTSUM+Transformer	43.25	Yes	Fine-tune BERT for Extractive Summarization	2019-03-25	Code
13	UniLM (Abstractive Summarization)	43.08	Yes	Unified Language Model Pre-training for Natural ...	2019-05-08	Code
14	Selector+Pointer Generator	41.72	No	Mixture Content Selection for Diverse Sequence G...	2019-09-04	Code
15	NeuSUM	41.59	No	Neural Document Summarization by Jointly Learnin...	2018-07-06	Code
16	Bottom-Up Sum	41.22	No	Bottom-Up Abstractive Summarization	2018-08-31	Code
17	TaLK Convolutions (Deep)	40.59	No	Time-aware Large Kernel Convolutions	2020-02-08	Code
18	Lead-3	40.34	No	Get To The Point: Summarization with Pointer-Gen...	2017-04-14	Code
19	TaLK Convolutions (Standard)	40.03	No	Time-aware Large Kernel Convolutions	2020-02-08	Code
20	ML + RL (Paulus et al., 2017)	39.87	No	A Deep Reinforced Model for Abstractive Summariz...	2017-05-11	Code
21	DynamicConv	39.84	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
22	LightConv	39.52	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
23	Synthesizer (R+V)	38.57	No	Synthesizer: Rethinking Self-Attention in Transf...	2020-05-02	Code
24	ML + Intra-Attention (Paulus et al., 2017)	38.3	No	A Deep Reinforced Model for Abstractive Summariz...	2017-05-11	Code
25	C2F + ALTERNATE	31.1	No	-	-	-
26	GPT-2	29.34	Yes	-	-	Code

#1Scrambled code + broken (alter)SOTA
48.18
ROUGE-1· 2022-10-25
Universal Evasion Attacks on Summarization Scoring Code
#2PEGASUS + SummaRerankerSOTA
47.16
ROUGE-1· 2022-03-13
SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization Code
#3Fourier Transformer
44.76
ROUGE-1· 2023-05-24
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator Code
#4GLM-XXLargeSOTA
44.7
ROUGE-1· 2021-03-18
GLM: General Language Model Pretraining with Autoregressive Blank Infilling Code
#5HAT-BART
44.48
ROUGE-1· 2021-04-15
Hierarchical Learning for Generation with Long Source Sequences
#6MatchSum (RoBERTa-base)SOTA
44.41
ROUGE-1· 2020-04-19
Extractive Summarization as Text Matching Code
#7Hie-BART
44.35
ROUGE-1
No paper
#8MatchSum (BERT-base)
44.22
ROUGE-1· 2020-04-19
Extractive Summarization as Text Matching Code
#9BertSumExtSOTA
43.85
ROUGE-1· Extra Data· 2019-08-22
Text Summarization with Pretrained Encoders Code
#10BigBird-Pegasus
43.84
ROUGE-1· 2020-07-28
Big Bird: Transformers for Longer Sequences Code
#11T5-11B
43.52
ROUGE-1· Extra Data· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#12BERTSUM+TransformerSOTA
43.25
ROUGE-1· Extra Data· 2019-03-25
Fine-tune BERT for Extractive Summarization Code
#13UniLM (Abstractive Summarization)
43.08
ROUGE-1· Extra Data· 2019-05-08
Unified Language Model Pre-training for Natural Language Understanding and Generation Code
#14Selector+Pointer Generator
41.72
ROUGE-1· 2019-09-04
Mixture Content Selection for Diverse Sequence Generation Code
#15NeuSUMSOTA
41.59
ROUGE-1· 2018-07-06
Neural Document Summarization by Jointly Learning to Score and Select Sentences Code
#16Bottom-Up Sum
41.22
ROUGE-1· 2018-08-31
Bottom-Up Abstractive Summarization Code
#17TaLK Convolutions (Deep)
40.59
ROUGE-1· 2020-02-08
Time-aware Large Kernel Convolutions Code
#18Lead-3SOTA
40.34
ROUGE-1· 2017-04-14
Get To The Point: Summarization with Pointer-Generator Networks Code
#19TaLK Convolutions (Standard)
40.03
ROUGE-1· 2020-02-08
Time-aware Large Kernel Convolutions Code
#20ML + RL (Paulus et al., 2017)
39.87
ROUGE-1· 2017-05-11
A Deep Reinforced Model for Abstractive Summarization Code
#21DynamicConv
39.84
ROUGE-1· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#22LightConv
39.52
ROUGE-1· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#23Synthesizer (R+V)
38.57
ROUGE-1· 2020-05-02
Synthesizer: Rethinking Self-Attention in Transformer Models Code
#24ML + Intra-Attention (Paulus et al., 2017)
38.3
ROUGE-1· 2017-05-11
A Deep Reinforced Model for Abstractive Summarization Code
#25C2F + ALTERNATE
31.1
ROUGE-1
No paper
#26GPT-2
29.34
ROUGE-1· Extra Data
No paperCode