Text Summarization on GigaWord

Metric: ROUGE-2 (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	ROUGE-2▼	Extra Data	Paper	Date↕	Code
1	OpenAI/o3-mini	54.22	No	-	-	-
2	Riple/Saanvi-v0.1	45.58	No	-	-	-
3	Pegasus+DotProd	21	Yes	-	-	-
4	BART-RXF	20.69	No	Better Fine-Tuning by Reducing Representational ...	2020-08-06	Code
5	OFA	20.66	No	OFA: Unifying Architectures, Tasks, and Modaliti...	2022-02-07	Code
6	MUPPET BART Large	20.54	Yes	Muppet: Massive Multi-task Representations with ...	2021-01-26	Code
7	ControlCopying + SBWR	20.47	No	Controlling the Amount of Verbatim Copying in Ab...	2019-11-23	Code
8	Transformer+Wdrop	20.45	Yes	Rethinking Perturbations in Encoder-Decoders for...	2021-04-05	Code
9	ProphetNet	20.42	Yes	ProphetNet: Predicting Future N-gram for Sequenc...	2020-01-13	Code
10	Transformer+Rep(Uni)	20.4	Yes	Rethinking Perturbations in Encoder-Decoders for...	2021-04-05	Code
11	Best Summary Length	20.4	No	A New Approach to Overgenerating and Scoring Abs...	2021-04-05	Code
12	ControlCopying + BPNorm	20.38	No	Controlling the Amount of Verbatim Copying in Ab...	2019-11-23	Code
13	PALM	20.37	No	PALM: Pre-training an Autoencoding&Autoregressiv...	2020-04-14	Code
14	ERNIE-GENLARGE (large-scale text corpora)	20.34	Yes	ERNIE-GEN: An Enhanced Multi-Flow Pre-training a...	2020-01-26	Code
15	ERNIE-GENLARGE	20.25	Yes	ERNIE-GEN: An Enhanced Multi-Flow Pre-training a...	2020-01-26	Code
16	UniLM	20.05	Yes	Unified Language Model Pre-training for Natural ...	2019-05-08	Code
17	ERNIE-GENBASE	20.04	Yes	ERNIE-GEN: An Enhanced Multi-Flow Pre-training a...	2020-01-26	Code
18	PEGASUS	19.86	Yes	PEGASUS: Pre-training with Extracted Gap-sentenc...	2019-12-18	Code
19	BiSET	19.78	No	BiSET: Bi-directional Selective Encoding with Te...	2019-06-12	Code
20	MASS	19.71	Yes	MASS: Masked Sequence to Sequence Pre-training f...	2019-05-07	Code
21	Mask Attention Network	19.46	No	Mask Attention Networks: Rethinking and Strength...	2021-03-25	Code
22	Re^3 Sum	19.03	No	-	-	-
23	Transformer	18.9	No	Attention Is All You Need	2017-06-12	Code
24	JointParsing	18.85	No	Joint Parsing and Generation for Abstractive Sum...	2019-11-23	Code
25	Reinforced-Topic-ConvS2S	18.29	No	A Reinforced Topic-Aware Convolutional Sequence-...	2018-05-09	-
26	CGU	18	No	Global Encoding for Abstractive Summarization	2018-05-10	Code
27	Pointer + Coverage + EntailmentGen + QuestionGen	17.76	No	Soft Layer-Specific Multi-Task Summarization wit...	2018-05-28	-
28	words-lvt5k-1sent	17.7	No	Abstractive Text Summarization Using Sequence-to...	2016-02-19	Code
29	Struct+2Way+Word	17.66	No	Structure-Infused Copy Mechanisms for Abstractiv...	2018-06-14	Code
30	FTSum_g	17.65	No	Faithful to the Original: Fact Aware Neural Abst...	2017-11-13	-
31	DRGD	17.57	No	Deep Recurrent Generative Decoder for Abstractiv...	2017-08-02	Code
32	SEASS	17.54	No	Selective Encoding for Abstractive Sentence Summ...	2017-04-24	Code
33	EndDec+WFE	17.31	No	Cutting-off Redundant Repeating Generations for ...	2016-12-31	-
34	Seq2seq + selective + MTL + ERAM	17.27	No	-	-	-
35	Concept pointer+DS	17.1	No	Concept Pointer Network for Abstractive Summariz...	2019-10-18	Code
36	Concept pointer+RL	16.97	No	Concept Pointer Network for Abstractive Summariz...	2019-10-18	Code
37	Seq2seq + E2T_cnn	16.66	No	Entity Commonsense Representation for Neural Abs...	2018-06-14	Code
38	RAS-Elman	15.97	No	-	-	-
39	Contextual Match	10.05	No	Simple Unsupervised Summarization by Contextual ...	2019-07-31	Code

#1OpenAI/o3-mini
54.22
ROUGE-2
No paper
#2Riple/Saanvi-v0.1
45.58
ROUGE-2
No paper
#3Pegasus+DotProd
21
ROUGE-2· Extra Data
No paper
#4BART-RXFSOTA
20.69
ROUGE-2· 2020-08-06
Better Fine-Tuning by Reducing Representational Collapse Code
#5OFA
20.66
ROUGE-2· 2022-02-07
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework Code
#6MUPPET BART Large
20.54
ROUGE-2· Extra Data· 2021-01-26
Muppet: Massive Multi-task Representations with Pre-Finetuning Code
#7ControlCopying + SBWRSOTA
20.47
ROUGE-2· 2019-11-23
Controlling the Amount of Verbatim Copying in Abstractive Summarization Code
#8Transformer+Wdrop
20.45
ROUGE-2· Extra Data· 2021-04-05
Rethinking Perturbations in Encoder-Decoders for Fast Training Code
#9ProphetNet
20.42
ROUGE-2· Extra Data· 2020-01-13
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training Code
#10Transformer+Rep(Uni)
20.4
ROUGE-2· Extra Data· 2021-04-05
Rethinking Perturbations in Encoder-Decoders for Fast Training Code
#11Best Summary Length
20.4
ROUGE-2· 2021-04-05
A New Approach to Overgenerating and Scoring Abstractive Summaries Code
#12ControlCopying + BPNorm
20.38
ROUGE-2· 2019-11-23
Controlling the Amount of Verbatim Copying in Abstractive Summarization Code
#13PALM
20.37
ROUGE-2· 2020-04-14
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation Code
#14ERNIE-GENLARGE (large-scale text corpora)
20.34
ROUGE-2· Extra Data· 2020-01-26
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation Code
#15ERNIE-GENLARGE
20.25
ROUGE-2· Extra Data· 2020-01-26
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation Code
#16UniLMSOTA
20.05
ROUGE-2· Extra Data· 2019-05-08
Unified Language Model Pre-training for Natural Language Understanding and Generation Code
#17ERNIE-GENBASE
20.04
ROUGE-2· Extra Data· 2020-01-26
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation Code
#18PEGASUS
19.86
ROUGE-2· Extra Data· 2019-12-18
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization Code
#19BiSET
19.78
ROUGE-2· 2019-06-12
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization Code
#20MASSSOTA
19.71
ROUGE-2· Extra Data· 2019-05-07
MASS: Masked Sequence to Sequence Pre-training for Language Generation Code
#21Mask Attention Network
19.46
ROUGE-2· 2021-03-25
Mask Attention Networks: Rethinking and Strengthen Transformer Code
#22Re^3 Sum
19.03
ROUGE-2
No paper
#23TransformerSOTA
18.9
ROUGE-2· 2017-06-12
Attention Is All You Need Code
#24JointParsing
18.85
ROUGE-2· 2019-11-23
Joint Parsing and Generation for Abstractive Summarization Code
#25Reinforced-Topic-ConvS2S
18.29
ROUGE-2· 2018-05-09
A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization
#26CGU
18
ROUGE-2· 2018-05-10
Global Encoding for Abstractive Summarization Code
#27Pointer + Coverage + EntailmentGen + QuestionGen
17.76
ROUGE-2· 2018-05-28
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation
#28words-lvt5k-1sentSOTA
17.7
ROUGE-2· 2016-02-19
Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond Code
#29Struct+2Way+Word
17.66
ROUGE-2· 2018-06-14
Structure-Infused Copy Mechanisms for Abstractive Summarization Code
#30FTSum_g
17.65
ROUGE-2· 2017-11-13
Faithful to the Original: Fact Aware Neural Abstractive Summarization
#31DRGD
17.57
ROUGE-2· 2017-08-02
Deep Recurrent Generative Decoder for Abstractive Text Summarization Code
#32SEASS
17.54
ROUGE-2· 2017-04-24
Selective Encoding for Abstractive Sentence Summarization Code
#33EndDec+WFE
17.31
ROUGE-2· 2016-12-31
Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
#34Seq2seq + selective + MTL + ERAM
17.27
ROUGE-2
No paper
#35Concept pointer+DS
17.1
ROUGE-2· 2019-10-18
Concept Pointer Network for Abstractive Summarization Code
#36Concept pointer+RL
16.97
ROUGE-2· 2019-10-18
Concept Pointer Network for Abstractive Summarization Code
#37Seq2seq + E2T_cnn
16.66
ROUGE-2· 2018-06-14
Entity Commonsense Representation for Neural Abstractive Summarization Code
#38RAS-Elman
15.97
ROUGE-2
No paper
#39Contextual Match
10.05
ROUGE-2· 2019-07-31
Simple Unsupervised Summarization by Contextual Matching Code