Abstractive Text 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	BRIO	47.78	No	BRIO: Bringing Order to Abstractive Summarization	2022-03-31	Code
3	Pegasus	47.36	No	Calibrating Sequence likelihood Improves Conditi...	2022-09-30	-
4	PEGASUS + SummaReranker	47.16	No	SummaReranker: A Multi-Task Mixture-of-Experts R...	2022-03-13	Code
5	Scrambled code + broken	46.71	No	Universal Evasion Attacks on Summarization Scoring	2022-10-25	Code
6	BART + SimCLS	46.67	No	SimCLS: A Simple Framework for Contrastive Learn...	2021-06-03	Code
7	SEASON	46.27	No	Salience Allocation as Guidance for Abstractive ...	2022-10-22	Code
8	Fourier Transformer	44.76	No	Fourier Transformer: Fast Long Range Modeling by...	2023-05-24	Code
9	GLM-XXLarge	44.7	Yes	GLM: General Language Model Pretraining with Aut...	2021-03-18	Code
10	BART + R-Drop	44.51	No	R-Drop: Regularized Dropout for Neural Networks	2021-06-28	Code
11	CoCoNet + CoCoPretrain	44.5	Yes	-	-	Code
12	MUPPET BART Large	44.45	No	Muppet: Massive Multi-task Representations with ...	2021-01-26	Code
13	CoCoNet	44.39	No	-	-	Code
14	BART+R3F	44.38	No	Better Fine-Tuning by Reducing Representational ...	2020-08-06	Code
15	ERNIE-GENLARGE (large-scale text corpora)	44.31	Yes	ERNIE-GEN: An Enhanced Multi-Flow Pre-training a...	2020-01-26	Code
16	PALM	44.3	No	PALM: Pre-training an Autoencoding&Autoregressiv...	2020-04-14	Code
17	ProphetNet	44.2	Yes	ProphetNet: Predicting Future N-gram for Sequenc...	2020-01-13	Code
18	PEGASUS	44.17	Yes	PEGASUS: Pre-training with Extracted Gap-sentenc...	2019-12-18	Code
19	BART	44.16	No	BART: Denoising Sequence-to-Sequence Pre-trainin...	2019-10-29	Code
20	ERNIE-GENLARGE	44.02	No	ERNIE-GEN: An Enhanced Multi-Flow Pre-training a...	2020-01-26	Code
21	LongT5	43.94	No	LongT5: Efficient Text-To-Text Transformer for L...	2021-12-15	Code
22	T5	43.52	No	Exploring the Limits of Transfer Learning with a...	2019-10-23	Code
23	SRformer-BART	43.19	No	Segmented Recurrent Transformer: An Efficient Se...	2023-05-24	Code
24	UniLMv2	43.16	Yes	UniLMv2: Pseudo-Masked Language Models for Unifi...	2020-02-28	Code
25	UniLM	43.08	Yes	Unified Language Model Pre-training for Natural ...	2019-05-08	Code
26	ERNIE-GENBASE	42.3	Yes	ERNIE-GEN: An Enhanced Multi-Flow Pre-training a...	2020-01-26	Code
27	BertSumExtAbs	42.13	Yes	Text Summarization with Pretrained Encoders	2019-08-22	Code
28	BERT-ext + abs + RL + rerank	41.9	No	Summary Level Training of Sentence Rewriting for...	2019-09-19	-
29	Selector & Pointer-Generator	41.72	Yes	Mixture Content Selection for Diverse Sequence G...	2019-09-04	Code
30	Two-Stage + RL	41.71	No	Pretraining-Based Natural Language Generation fo...	2019-02-25	Code
31	DCA	41.69	Yes	Deep Communicating Agents for Abstractive Summar...	2018-03-27	-
32	Li et al.	41.54	No	-	-	-
33	rnn-ext + RL	41.47	No	Fast Abstractive Summarization with Reinforce-Se...	2018-05-28	Code
34	EditNet	41.42	No	An Editorial Network for Enhanced Document Summa...	2019-02-27	-
35	Bottom-Up Summarization	41.22	No	Bottom-Up Abstractive Summarization	2018-08-31	Code
36	Mask Attention Network	40.98	No	Mask Attention Networks: Rethinking and Strength...	2021-03-25	Code
37	Subformer-base	40.9	No	-	-	-
38	rnn-ext + abs + RL + rerank	40.88	No	Fast Abstractive Summarization with Reinforce-Se...	2018-05-28	Code
39	end2end w/ inconsistency loss	40.68	No	A Unified Model for Extractive and Abstractive S...	2018-05-16	Code
40	RL + pg + cbdec	40.66	No	Closed-Book Training to Improve Summarization En...	2018-09-12	-
41	ROUGESal+Ent RL	40.43	No	Multi-Reward Reinforced Summarization with Salie...	2018-04-17	-
42	LEAD-3	40.42	No	Abstractive Text Summarization Using Sequence-to...	2016-02-19	Code
43	Li et al.	40.3	No	-	-	-
44	ML+RL ROUGE+Novel, with LM	40.19	No	Improving Abstraction in Text Summarization	2018-08-23	-
45	Dynamic Conv	39.84	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
46	Pointer + Coverage + EntailmentGen + QuestionGen	39.81	No	Soft Layer-Specific Multi-Task Summarization wit...	2018-05-28	-
47	PTGEN + Coverage	39.53	No	Get To The Point: Summarization with Pointer-Gen...	2017-04-14	Code
48	PTGEN + Coverage	39.53	No	Get To The Point: Summarization with Pointer-Gen...	2017-04-14	Code
49	Pointer-Generator + Coverage	39.53	No	Get To The Point: Summarization with Pointer-Gen...	2017-04-14	Code
50	Transformer	39.5	No	Attention Is All You Need	2017-06-12	Code
51	Summary Loop Unsup	37.7	No	The Summary Loop: Learning to Write Abstractive ...	2021-05-11	Code

#1Scrambled code + broken (alter)SOTA
48.18
ROUGE-1· 2022-10-25
Universal Evasion Attacks on Summarization Scoring Code
#2BRIOSOTA
47.78
ROUGE-1· 2022-03-31
BRIO: Bringing Order to Abstractive Summarization Code
#3Pegasus
47.36
ROUGE-1· 2022-09-30
Calibrating Sequence likelihood Improves Conditional Language Generation
#4PEGASUS + SummaRerankerSOTA
47.16
ROUGE-1· 2022-03-13
SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization Code
#5Scrambled code + broken
46.71
ROUGE-1· 2022-10-25
Universal Evasion Attacks on Summarization Scoring Code
#6BART + SimCLSSOTA
46.67
ROUGE-1· 2021-06-03
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization Code
#7SEASON
46.27
ROUGE-1· 2022-10-22
Salience Allocation as Guidance for Abstractive Summarization Code
#8Fourier Transformer
44.76
ROUGE-1· 2023-05-24
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator Code
#9GLM-XXLargeSOTA
44.7
ROUGE-1· Extra Data· 2021-03-18
GLM: General Language Model Pretraining with Autoregressive Blank Infilling Code
#10BART + R-Drop
44.51
ROUGE-1· 2021-06-28
R-Drop: Regularized Dropout for Neural Networks Code
#11CoCoNet + CoCoPretrain
44.5
ROUGE-1· Extra Data
No paperCode
#12MUPPET BART LargeSOTA
44.45
ROUGE-1· 2021-01-26
Muppet: Massive Multi-task Representations with Pre-Finetuning Code
#13CoCoNet
44.39
ROUGE-1
No paperCode
#14BART+R3FSOTA
44.38
ROUGE-1· 2020-08-06
Better Fine-Tuning by Reducing Representational Collapse Code
#15ERNIE-GENLARGE (large-scale text corpora)SOTA
44.31
ROUGE-1· Extra Data· 2020-01-26
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation Code
#16PALM
44.3
ROUGE-1· 2020-04-14
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation Code
#17ProphetNetSOTA
44.2
ROUGE-1· Extra Data· 2020-01-13
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training Code
#18PEGASUSSOTA
44.17
ROUGE-1· Extra Data· 2019-12-18
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization Code
#19BARTSOTA
44.16
ROUGE-1· 2019-10-29
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension Code
#20ERNIE-GENLARGE
44.02
ROUGE-1· 2020-01-26
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation Code
#21LongT5
43.94
ROUGE-1· 2021-12-15
LongT5: Efficient Text-To-Text Transformer for Long Sequences Code
#22T5SOTA
43.52
ROUGE-1· 2019-10-23
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Code
#23SRformer-BART
43.19
ROUGE-1· 2023-05-24
Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model Code
#24UniLMv2
43.16
ROUGE-1· Extra Data· 2020-02-28
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training Code
#25UniLMSOTA
43.08
ROUGE-1· Extra Data· 2019-05-08
Unified Language Model Pre-training for Natural Language Understanding and Generation Code
#26ERNIE-GENBASE
42.3
ROUGE-1· Extra Data· 2020-01-26
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation Code
#27BertSumExtAbs
42.13
ROUGE-1· Extra Data· 2019-08-22
Text Summarization with Pretrained Encoders Code
#28BERT-ext + abs + RL + rerank
41.9
ROUGE-1· 2019-09-19
Summary Level Training of Sentence Rewriting for Abstractive Summarization
#29Selector & Pointer-Generator
41.72
ROUGE-1· Extra Data· 2019-09-04
Mixture Content Selection for Diverse Sequence Generation Code
#30Two-Stage + RLSOTA
41.71
ROUGE-1· 2019-02-25
Pretraining-Based Natural Language Generation for Text Summarization Code
#31DCASOTA
41.69
ROUGE-1· Extra Data· 2018-03-27
Deep Communicating Agents for Abstractive Summarization
#32Li et al.
41.54
ROUGE-1
No paper
#33rnn-ext + RL
41.47
ROUGE-1· 2018-05-28
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting Code
#34EditNet
41.42
ROUGE-1· 2019-02-27
An Editorial Network for Enhanced Document Summarization
#35Bottom-Up Summarization
41.22
ROUGE-1· 2018-08-31
Bottom-Up Abstractive Summarization Code
#36Mask Attention Network
40.98
ROUGE-1· 2021-03-25
Mask Attention Networks: Rethinking and Strengthen Transformer Code
#37Subformer-base
40.9
ROUGE-1
No paper
#38rnn-ext + abs + RL + rerank
40.88
ROUGE-1· 2018-05-28
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting Code
#39end2end w/ inconsistency loss
40.68
ROUGE-1· 2018-05-16
A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss Code
#40RL + pg + cbdec
40.66
ROUGE-1· 2018-09-12
Closed-Book Training to Improve Summarization Encoder Memory
#41ROUGESal+Ent RL
40.43
ROUGE-1· 2018-04-17
Multi-Reward Reinforced Summarization with Saliency and Entailment
#42LEAD-3SOTA
40.42
ROUGE-1· 2016-02-19
Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond Code
#43Li et al.
40.3
ROUGE-1
No paper
#44ML+RL ROUGE+Novel, with LM
40.19
ROUGE-1· 2018-08-23
Improving Abstraction in Text Summarization
#45Dynamic Conv
39.84
ROUGE-1· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#46Pointer + Coverage + EntailmentGen + QuestionGen
39.81
ROUGE-1· 2018-05-28
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation
#47PTGEN + Coverage
39.53
ROUGE-1· 2017-04-14
Get To The Point: Summarization with Pointer-Generator Networks Code
#48PTGEN + Coverage
39.53
ROUGE-1· 2017-04-14
Get To The Point: Summarization with Pointer-Generator Networks Code
#49Pointer-Generator + Coverage
39.53
ROUGE-1· 2017-04-14
Get To The Point: Summarization with Pointer-Generator Networks Code
#50Transformer
39.5
ROUGE-1· 2017-06-12
Attention Is All You Need Code
#51Summary Loop Unsup
37.7
ROUGE-1· 2021-05-11
The Summary Loop: Learning to Write Abstractive Summaries Without Examples Code