SOTAVerified

Text Summarization

Text Summarization is a natural language processing (NLP) task that involves condensing a lengthy text document into a shorter, more compact version while still retaining the most important information and meaning. The goal is to produce a summary that accurately represents the content of the original text in a concise form.

There are different approaches to text summarization, including extractive methods that identify and extract important sentences or phrases from the text, and abstractive methods that generate new text based on the content of the original text.

Papers

Showing 201250 of 1340 papers

TitleStatusHype
TL;DR Progress: Multi-faceted Literature Exploration in Text SummarizationCode0
Explaining Veracity Predictions with Evidence Summarization: A Multi-Task Model ApproachCode0
RankSum An unsupervised extractive text summarization based on rank fusion0
Personalized Language Modeling from Personalized Human FeedbackCode1
Graph Neural Network and NER-Based Text Summarization0
A Survey of Large Language Models in Finance (FinLLMs)Code3
A Hybrid Strategy for Chat Transcript Summarization0
Identifying False Content and Hate Speech in Sinhala YouTube Videos by Analyzing the Audio0
PRE: A Peer Review Based Large Language Model Evaluator0
The Radiation Oncology NLP DatabaseCode1
Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions0
Hyperparameter-Free Approach for Faster Minimum Bayes Risk DecodingCode0
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning0
PersianLLaMA: Towards Building First Persian Large Language Model0
Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models0
Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation AccuracyCode2
Cross-Domain Robustness of Transformer-based Keyphrase Generation0
Exploiting Representation Bias for Data Distillation in Abstractive Text Summarization0
Nash Learning from Human Feedback0
Ascle: A Python Natural Language Processing Toolkit for Medical Text GenerationCode1
ChatGPT Application In Summarizing An Evolution Of Deep Learning Techniques In Imaging: A Qualitative Study0
Exploring Prompting Large Language Models as Explainable MetricsCode0
Responsible AI Considerations in Text Summarization Research: A Review of Current Practices0
DynaPipe: Optimizing Multi-task Training through Dynamic PipelinesCode1
Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization0
Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A SurveyCode0
Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable SummarizationCode1
GreekT5: A Series of Greek Sequence-to-Sequence Models for News SummarizationCode0
Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform0
OmniVec: Learning robust representations with cross modal sharing0
FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM0
An Introduction to Natural Language Processing Techniques and Framework for Clinical Implementation in Radiation Oncology0
The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization0
Boosting Summarization with Normalizing Flows and Aggressive TrainingCode0
Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer0
Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs0
Correction with Backtracking Reduces Hallucination in SummarizationCode0
Prevalence and prevention of large language model use in crowd work0
A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare0
Leveraging Deep Learning for Abstractive Code Summarization of Unofficial Documentation0
Controlled Randomness Improves the Performance of Transformer Models0
Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language ModelCode1
Open Information Extraction: A Review of Baseline Techniques, Approaches, and Applications0
Automatic News Summerization0
Instructive Dialogue Summarization with Query AggregationsCode0
Key-phrase boosted unsupervised summary generation for FinTech organization0
Metric Ensembles For Hallucination Detection0
Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT ModelsCode0
Surveying the Landscape of Text Summarization with Deep Learning: A Comprehensive Review0
Calibrating Likelihoods towards Consistency in Summarization Models0
Show:102550
← PrevPage 5 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OpenAI/o3-miniROUGE-160.12Unverified
2Riple/Saanvi-v0.1ROUGE-152.21Unverified
3Pegasus+DotProdROUGE-140.6Unverified
4BART-RXFROUGE-140.45Unverified
5MUPPET BART LargeROUGE-140.4Unverified
6Transformer+Rep(Uni)ROUGE-139.81Unverified
7OFAROUGE-139.81Unverified
8Transformer+WdropROUGE-139.66Unverified
9ProphetNetROUGE-139.51Unverified
10ERNIE-GENLARGE (large-scale text corpora)ROUGE-139.46Unverified
#ModelMetricClaimedVerifiedStatus
1Top Down Transformer (AdaPool) (464M)ROUGE-151.05Unverified
2eyeglaxsROUGE-150.34Unverified
3BART-LSROUGE-150.3Unverified
4LongT5ROUGE-150.23Unverified
5GoSum (extractive)ROUGE-149.83Unverified
6Lodoss-full-large (extractive)ROUGE-149.38Unverified
7MemSum (extractive)ROUGE-149.25Unverified
8Lodoss-full-base (extractive)ROUGE-148.93Unverified
9HAT-BARTROUGE-148.25Unverified
10GRETELROUGE-148.2Unverified
#ModelMetricClaimedVerifiedStatus
1Top Down Transformer (AdaPool) (464M)ROUGE-150.95Unverified
2BART-LSROUGE-150.2Unverified
3Pegasus-XROUGE-150Unverified
4ExtSum + oracle segmentation (extractive)ROUGE-149.49Unverified
5FactorSumROUGE-149.32Unverified
6ExtSum + supervised segmentation (extractive)ROUGE-149.11Unverified
7Lodoss-full-large (extractive)ROUGE-148.45Unverified
8MemSum (extractive)ROUGE-148.42Unverified
9LongT5ROUGE-148.35Unverified
10Lodoss-full-base (extractive)ROUGE-148.2Unverified
#ModelMetricClaimedVerifiedStatus
1SelfmemROUGE-150.3Unverified
2BRIOROUGE-149.07Unverified
3PEGASUS + SummaRerankerROUGE-148.12Unverified
4PEGASUS + SimCLSROUGE-147.61Unverified
5PEGASUSLARGEROUGE-147.21Unverified
6HAT-BARTROUGE-145.92Unverified
7BARTROUGE-145.14Unverified
8BertSumExtAbsROUGE-138.81Unverified
9T-ConvS2SROUGE-131.89Unverified
10Baseline : Extractive OracleROUGE-129.79Unverified
#ModelMetricClaimedVerifiedStatus
1HSSASROUGE-142.3Unverified
2SWAP-NETROUGE-141.6Unverified
3RNES w/o coherenceROUGE-141.25Unverified
4ML+RL ROUGE+Novel, with LMROUGE-140.02Unverified
5GANROUGE-139.92Unverified
6ML+RL, with intra-attentionROUGE-139.87Unverified
7rnn-ext + abs + RL + rerankROUGE-139.66Unverified
8SummaRuNNerROUGE-139.6Unverified
9Lead-3 baselineROUGE-139.2Unverified
10KIGN+Prediction-guideROUGE-138.95Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer+WDropROUGE-133.06Unverified
2Transformer+LRPE+PE+Re-ranking+EnsembleROUGE-132.85Unverified
3Transformer+LRPE+PE+ALONE+Re-rankingROUGE-132.57Unverified
4EndDec+WFEROUGE-132.28Unverified
5DRGDROUGE-131.79Unverified
6Reinforced-Topic-ConvS2SROUGE-131.15Unverified
7Seq2seq + selective + MTL + ERAMROUGE-129.33Unverified
8SEASSROUGE-129.21Unverified
9RAS-ElmanROUGE-128.97Unverified
10words-lvt5k-1sentROUGE-128.61Unverified
#ModelMetricClaimedVerifiedStatus
1OmniVec2ROUGE-159.1Unverified
2InstructDSROUGE-155.3Unverified
3MoCaROUGE-155.13Unverified
4PEGASUS 2B + SliCROUGE-154.37Unverified
5ConDigSumROUGE-154.3Unverified
6SICKROUGE-153.73Unverified
7HAT-CNNDMROUGE-153.01Unverified
8BART-LargeROUGE-152.6Unverified
9HAT-CNNDM RLROUGE-L48.84Unverified
10CriSPO 3-shotROUGE-147.2Unverified
#ModelMetricClaimedVerifiedStatus
1PEGASUS 2B + SLiCROUGE-132.03Unverified
2BART+R3FROUGE-130.31Unverified
3MUPPET BART LargeROUGE-130.3Unverified
4PEGASUS + SummaRerankerROUGE-129.83Unverified
5MatchSumROUGE-125.09Unverified
#ModelMetricClaimedVerifiedStatus
1PRIMERROUGE-147.6Unverified
2DeepPyramidionROUGE-147.15Unverified
3Blockwise (baseline)ROUGE-146.85Unverified
4Claude Instant + SigExtROUGE-145.2Unverified
#ModelMetricClaimedVerifiedStatus
1InstructDSRouge147.8Unverified
2OmniVec2Rouge147.6Unverified
3OmniVecRouge146.91Unverified
4SICKRouge146.26Unverified
#ModelMetricClaimedVerifiedStatus
1Luhn's algorithm (25 sentences)ROUGE-132Unverified
2Lead-kROUGE-125Unverified
3Lead-3ROUGE-117.5Unverified
4Full articleROUGE-116.98Unverified
#ModelMetricClaimedVerifiedStatus
1Echoes-Extractive-AbstractiveROUGE42.13Unverified
2BART-LSROUGE38.5Unverified
3Top Down Transformer (AdaPool) (464M)ROUGE38.3Unverified
#ModelMetricClaimedVerifiedStatus
1ERNIE-GENLARGE (large-scale text corpora)ROUGE-L33.23Unverified
2ERNIE-GENLARGEROUGE-L32.5Unverified
3ERNIE-GENBASEROUGE-L31.35Unverified
#ModelMetricClaimedVerifiedStatus
1BertSumROUGE-135.91Unverified
2MatchSum (BERT-base)ROUGE-131.85Unverified
3Pointer-generator + coverageROUGE-128.53Unverified
#ModelMetricClaimedVerifiedStatus
1LongT5ROUGE-176.87Unverified
2BigBird-PegasusROUGE-160.64Unverified
#ModelMetricClaimedVerifiedStatus
1BART-LSROUGE-162Unverified
2FactorSumROUGE-160.1Unverified
#ModelMetricClaimedVerifiedStatus
1Ground-truth transcript + Action with Hierarchical AttnContent F148.9Unverified
2BertSumContent F136.4Unverified
#ModelMetricClaimedVerifiedStatus
1CriSPO 3-shotROUGE-L54.1Unverified
2Claude Instant + SigExtROUGE-L31.9Unverified
#ModelMetricClaimedVerifiedStatus
1MiniLM-L12-multilingualSpearman Correlation30.67Unverified
2ContrieverSpearman Correlation30.36Unverified
#ModelMetricClaimedVerifiedStatus
1mBARThez (OrangeSum abstract)ROUGE-132.67Unverified
2BARThez (OrangeSum abstract)ROUGE-131.44Unverified
#ModelMetricClaimedVerifiedStatus
1CriSPO 3-shotROUGE-163.1Unverified
#ModelMetricClaimedVerifiedStatus
1HAT-CNNDMROUGE-152.27Unverified
#ModelMetricClaimedVerifiedStatus
1BigBird-PegasusROUGE-146.63Unverified
#ModelMetricClaimedVerifiedStatus
1MatchSumROUGE-124.86Unverified
#ModelMetricClaimedVerifiedStatus
1Longformer Encoder Decoderrouge138.65Unverified
#ModelMetricClaimedVerifiedStatus
1GCN HybridROUGE-233.88Unverified
#ModelMetricClaimedVerifiedStatus
1GenCompareSumROUGE-141.02Unverified
#ModelMetricClaimedVerifiedStatus
1SATSAvg. Test Rouge134.24Unverified