Document Summarization on CNN / Daily Mail

Metric: ROUGE-2 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	ROUGE-2▼	Extra Data	Paper	Date↕	Code
1	PEGASUS + SummaReranker	22.55	No	SummaReranker: A Multi-Task Mixture-of-Experts R...	2022-03-13	Code
2	Fourier Transformer	21.55	No	Fourier Transformer: Fast Long Range Modeling by...	2023-05-24	Code
3	T5-11B	21.55	Yes	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
4	GLM-XXLarge	21.4	No	GLM: General Language Model Pretraining with Aut...	2021-03-18	Code
5	Hie-BART	21.37	No	-	-	-
6	HAT-BART	21.31	No	Hierarchical Learning for Generation with Long S...	2021-04-15	-
7	BigBird-Pegasus	21.11	No	Big Bird: Transformers for Longer Sequences	2020-07-28	Code
8	MatchSum (RoBERTa-base)	20.86	No	Extractive Summarization as Text Matching	2020-04-19	Code
9	MatchSum (BERT-base)	20.62	No	Extractive Summarization as Text Matching	2020-04-19	Code
10	UniLM (Abstractive Summarization)	20.43	Yes	Unified Language Model Pre-training for Natural ...	2019-05-08	Code
11	BertSumExt	20.34	Yes	Text Summarization with Pretrained Encoders	2019-08-22	Code
12	BERTSUM+Transformer	20.24	Yes	Fine-tune BERT for Extractive Summarization	2019-03-25	Code
13	Scrambled code + broken (alter)	19.84	No	Universal Evasion Attacks on Summarization Scoring	2022-10-25	Code
14	NeuSUM	19.01	No	Neural Document Summarization by Jointly Learnin...	2018-07-06	Code
15	TaLK Convolutions (Deep)	18.97	No	Time-aware Large Kernel Convolutions	2020-02-08	Code
16	Selector+Pointer Generator	18.74	No	Mixture Content Selection for Diverse Sequence G...	2019-09-04	Code
17	Bottom-Up Sum	18.68	No	Bottom-Up Abstractive Summarization	2018-08-31	Code
18	TaLK Convolutions (Standard)	18.45	No	Time-aware Large Kernel Convolutions	2020-02-08	Code
19	Lead-3	17.7	No	Get To The Point: Summarization with Pointer-Gen...	2017-04-14	Code
20	DynamicConv	16.25	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
21	Synthesizer (R+V)	16.24	No	Synthesizer: Rethinking Self-Attention in Transf...	2020-05-02	Code
22	LightConv	15.97	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
23	ML + RL (Paulus et al., 2017)	15.82	No	A Deep Reinforced Model for Abstractive Summariz...	2017-05-11	Code
24	C2F + ALTERNATE	15.4	No	-	-	-
25	ML + Intra-Attention (Paulus et al., 2017)	14.81	No	A Deep Reinforced Model for Abstractive Summariz...	2017-05-11	Code
26	GPT-2	8.27	Yes	-	-	Code

#1PEGASUS + SummaRerankerSOTA
22.55
ROUGE-2· 2022-03-13
SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization Code
#2Fourier Transformer
21.55
ROUGE-2· 2023-05-24
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator Code
#3T5-11BSOTA
21.55
ROUGE-2· Extra Data· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#4GLM-XXLarge
21.4
ROUGE-2· 2021-03-18
GLM: General Language Model Pretraining with Autoregressive Blank Infilling Code
#5Hie-BART
21.37
ROUGE-2
No paper
#6HAT-BART
21.31
ROUGE-2· 2021-04-15
Hierarchical Learning for Generation with Long Source Sequences
#7BigBird-Pegasus
21.11
ROUGE-2· 2020-07-28
Big Bird: Transformers for Longer Sequences Code
#8MatchSum (RoBERTa-base)
20.86
ROUGE-2· 2020-04-19
Extractive Summarization as Text Matching Code
#9MatchSum (BERT-base)
20.62
ROUGE-2· 2020-04-19
Extractive Summarization as Text Matching Code
#10UniLM (Abstractive Summarization)SOTA
20.43
ROUGE-2· Extra Data· 2019-05-08
Unified Language Model Pre-training for Natural Language Understanding and Generation Code
#11BertSumExt
20.34
ROUGE-2· Extra Data· 2019-08-22
Text Summarization with Pretrained Encoders Code
#12BERTSUM+TransformerSOTA
20.24
ROUGE-2· Extra Data· 2019-03-25
Fine-tune BERT for Extractive Summarization Code
#13Scrambled code + broken (alter)
19.84
ROUGE-2· 2022-10-25
Universal Evasion Attacks on Summarization Scoring Code
#14NeuSUMSOTA
19.01
ROUGE-2· 2018-07-06
Neural Document Summarization by Jointly Learning to Score and Select Sentences Code
#15TaLK Convolutions (Deep)
18.97
ROUGE-2· 2020-02-08
Time-aware Large Kernel Convolutions Code
#16Selector+Pointer Generator
18.74
ROUGE-2· 2019-09-04
Mixture Content Selection for Diverse Sequence Generation Code
#17Bottom-Up Sum
18.68
ROUGE-2· 2018-08-31
Bottom-Up Abstractive Summarization Code
#18TaLK Convolutions (Standard)
18.45
ROUGE-2· 2020-02-08
Time-aware Large Kernel Convolutions Code
#19Lead-3SOTA
17.7
ROUGE-2· 2017-04-14
Get To The Point: Summarization with Pointer-Generator Networks Code
#20DynamicConv
16.25
ROUGE-2· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#21Synthesizer (R+V)
16.24
ROUGE-2· 2020-05-02
Synthesizer: Rethinking Self-Attention in Transformer Models Code
#22LightConv
15.97
ROUGE-2· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#23ML + RL (Paulus et al., 2017)
15.82
ROUGE-2· 2017-05-11
A Deep Reinforced Model for Abstractive Summarization Code
#24C2F + ALTERNATE
15.4
ROUGE-2
No paper
#25ML + Intra-Attention (Paulus et al., 2017)
14.81
ROUGE-2· 2017-05-11
A Deep Reinforced Model for Abstractive Summarization Code
#26GPT-2
8.27
ROUGE-2· Extra Data
No paperCode