Abstractive Text Summarization

Abstractive Text Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The generated summaries potentially contain new phrases and sentences that may not appear in the source text.

Source: Generative Adversarial Network for Abstractive Text Summarization

Image credit: Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 276–300 of 846 papers

Title	Date	Tasks	Status	Hype
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents	May 25, 2022	Abstractive Text SummarizationDisentanglement	CodeCode Available	1
Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors	May 25, 2022	Abstractive Text Summarization	CodeCode Available	1
Lossless Acceleration for Seq2seq Generation with Aggressive Decoding	May 20, 2022	Abstractive Text SummarizationGPU	CodeCode Available	0
FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization	May 16, 2022	Abstractive Text SummarizationContrastive Learning	CodeCode Available	1
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation	May 13, 2022	Abstractive Text SummarizationDecoder	CodeCode Available	1
Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization	May 12, 2022	Abstractive Text SummarizationNatural Language Inference	CodeCode Available	0
Few-shot Mining of Naturally Occurring Inputs and Outputs	May 9, 2022	Abstractive Text SummarizationData Augmentation	—Unverified	0
Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking	May 4, 2022	Abstractive Text Summarization	CodeCode Available	1
Efficient Few-Shot Fine-Tuning for Opinion Summarization	May 4, 2022	Abstractive Text SummarizationOpinion Summarization	CodeCode Available	0
RNSum: A Large-Scale Dataset for Automatic Release Note Generation via Commit Logs Summarization	May 1, 2022	Abstractive Text Summarization	—Unverified	0
Length Control in Abstractive Summarization by Pretraining Information Selection	May 1, 2022	Abstractive Text Summarization	CodeCode Available	0
FilipN@LT-EDI-ACL2022-Detecting signs of Depression from Social Media: Examining the use of summarization methods as data augmentation for text classification	May 1, 2022	Abstractive Text SummarizationClassification	CodeCode Available	0
NLPOP: a Dataset for Popularity Prediction of Promoted NLP Research on Twitter	May 1, 2022	Abstractive Text SummarizationCitation Recommendation	CodeCode Available	0
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation	May 1, 2022	Abstractive Text SummarizationCross-Lingual Abstractive Summarization	CodeCode Available	1
Meta-X_NLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation	May 1, 2022	Abstractive Text SummarizationCross-Lingual Transfer	—Unverified	0
Large-Scale Multi-Document Summarization with Information Extraction and Compression	May 1, 2022	Abstractive Text SummarizationDocument Summarization	—Unverified	0
Two New Datasets for Italian-Language Abstractive Text Summarization	Apr 29, 2022	Abstractive Text SummarizationArticles	CodeCode Available	0
Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization	Apr 28, 2022	Abstractive Text SummarizationWorld Knowledge	—Unverified	0
WikiMulti: a Corpus for Cross-Lingual Summarization	Apr 23, 2022	Abstractive Text SummarizationArticles	CodeCode Available	0
Spurious Correlations in Reference-Free Evaluation of Text Generation	Apr 21, 2022	Abstractive Text SummarizationText Generation	—Unverified	0
A Survey on Neural Abstractive Summarization Methods and Factual Consistency of Summarization	Apr 20, 2022	Abstractive Text Summarization	—Unverified	0
Factual Error Correction for Abstractive Summaries Using Entity Retrieval	Apr 18, 2022	Abstractive Text SummarizationEntity Retrieval	—Unverified	0
FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations	Apr 13, 2022	Abstractive Text SummarizationARC	CodeCode Available	1
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization	Apr 9, 2022	Abstractive Text SummarizationDecoder	—Unverified	0
Abstractive summarization of hospitalisation histories with transformer networks	Apr 5, 2022	Abstractive Text SummarizationDecoder	—Unverified	0

Show:10 25 50

← PrevPage 12 of 34Next →

All datasets CNN / Daily Mail Abstractive Text Summarization from Il Post vietnews Abstractive Text Summarization from Fanpage EDUsum CNN/Daily Mail MLSum-it WITS AESLC eLife Inshorts News MLSUM de

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Scrambled code + broken (alter)	ROUGE-1	48.18	—	Unverified
2	BRIO	ROUGE-1	47.78	—	Unverified
3	Pegasus	ROUGE-1	47.36	—	Unverified
4	PEGASUS + SummaReranker	ROUGE-1	47.16	—	Unverified
5	Scrambled code + broken	ROUGE-1	46.71	—	Unverified
6	BART + SimCLS	ROUGE-1	46.67	—	Unverified
7	SEASON	ROUGE-1	46.27	—	Unverified
8	Fourier Transformer	ROUGE-1	44.76	—	Unverified
9	GLM-XXLarge	ROUGE-1	44.7	—	Unverified
10	BART + R-Drop	ROUGE-1	44.51	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART	ROUGE-1	38.91	—	Unverified
2	mBART	ROUGE-1	38.91	—	Unverified
3	BART-IT	ROUGE-1	37.31	—	Unverified
4	mT5	ROUGE-1	35.04	—	Unverified
5	IT5	ROUGE-1	33.78	—	Unverified
6	IT5-base	ROUGE-1	32.88	—	Unverified
7	Pegasus-CNN/DM (eng-it translation)	ROUGE-1	23.96	—	Unverified
8	Pegasus-XSum (eng-it translation)	ROUGE-1	21.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Kết quả nghiên cứu	Rouge-1	67.8	—	Unverified
2	ViT5 large	Rouge-1	63.37	—	Unverified
3	ViT5 base	Rouge-1	62.77	—	Unverified
4	BARTpho	Rouge-1	61.14	—	Unverified
5	mBART	Rouge-1	59.81	—	Unverified
6	mT5	Rouge-1	58.05	—	Unverified
7	Transformer	Rouge-1	57.56	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART	ROUGE-1	36.52	—	Unverified
2	mBART	ROUGE-1	36.5	—	Unverified
3	BART-IT	ROUGE-1	35.42	—	Unverified
4	mT5	ROUGE-1	34.13	—	Unverified
5	IT5-base	ROUGE-1	33.99	—	Unverified
6	IT5	ROUGE-1	33.83	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GP_Step_Sim	ROUGE-1	64.48	—	Unverified
2	NEZHA	ROUGE-1	63.91	—	Unverified
3	RoBERTa	ROUGE-1	63.22	—	Unverified
4	BERT	ROUGE-1	62.37	—	Unverified
5	Seq2seq	ROUGE-1	48.62	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART (TextBox 2.0)	ROUGE-1	44.47	—	Unverified
2	SEGMENT	ROUGE-1	42.1	—	Unverified
3	CriSPO 3-shot	ROUGE-1	42.1	—	Unverified
4	Claude Instant + SigExt	ROUGE-1	42	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART	rouge1	19.35	—	Unverified
2	IT5	rouge1	19.29	—	Unverified
3	Pegasus-CNN/DM (eng-it translation)	rouge1	16.97	—	Unverified
4	Pegasus-XSum (eng-it translation)	rouge1	15.17	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BART-IT	ROUGE-1	42.32	—	Unverified
2	mT5	ROUGE-1	40.6	—	Unverified
3	mBART	ROUGE-1	39.32	—	Unverified
4	IT5-base	ROUGE-1	37.98	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PEGASUS	ROUGE-1	37.68	—	Unverified
2	Multi-Stage Extractor/Abstractor	ROUGE-1	23.67	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Two stage LLMs	Test ROGUE-1	0.46	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	T2SAM	ROUGE	48.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART	METEOR	0.44	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mBART	METEOR	0.21	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Two stage LLMs	Test ROGUE-1	0.44	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BertSum	Content F1	29.8	—	Unverified