SOTAVerified

Document Summarization

Automatic Document Summarization is the task of rewriting a document into its shorter form while still retaining its important content. The most popular two paradigms are extractive approaches and abstractive approaches. Extractive approaches generate summaries by extracting parts of the original document (usually sentences), while abstractive methods may generate new words or phrases which are not in the original document.

Source: HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 760 papers

TitleStatusHype
On Generating Extended Summaries of Long DocumentsCode1
DebateSum: A large-scale argument mining and summarization datasetCode1
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific ArticlesCode1
AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document SummarizationCode1
Dimsum @LaySumm 20: BART-based Approach for Scientific Document SummarizationCode1
Unsupervised Extractive Summarization by Pre-training Hierarchical TransformersCode1
Quantitative Argument Summarization and Beyond: Cross-Domain Key Point AnalysisCode1
Unsupervised Reference-Free Summary Quality Evaluation via Contrastive LearningCode1
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement LearningCode1
Sparsifying Transformer Models with Trainable Representation PoolingCode1
Summary-Source Proposition-level Alignment: Task, Datasets and Supervised BaselineCode1
Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document SummarizationCode1
SummPip: Unsupervised Multi-Document Summarization with Sentence Graph CompressionCode1
Pre-training via ParaphrasingCode1
DynE: Dynamic Ensemble Decoding for Multi-Document SummarizationCode1
A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events PortalCode1
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document SummarizationCode1
CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information ManagementCode1
On Faithfulness and Factuality in Abstractive SummarizationCode1
Synthesizer: Rethinking Self-Attention in Transformer ModelsCode1
Screenplay Summarization Using Latent Narrative StructureCode1
Heterogeneous Graph Neural Networks for Extractive Document SummarizationCode1
Extractive Summarization as Text MatchingCode1
A Divide-and-Conquer Approach to the Summarization of Long DocumentsCode1
AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document SummarizationCode1
unarXive: A Large Scholarly Data Set with Publications' Full-Text, Annotated In-Text Citations, and Links to MetadataCode1
GameWikiSum: a Novel Large Multi-Document Summarization DatasetCode1
Time-aware Large Kernel ConvolutionsCode1
Text Summarization with Pretrained EncodersCode1
Language Models are Unsupervised Multitask LearnersCode1
Bottom-Up Abstractive SummarizationCode1
Monotonic Chunkwise AttentionCode1
Monotonic Chunkwise AttentionCode1
Get To The Point: Summarization with Pointer-Generator NetworksCode1
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of DocumentsCode1
GenerationPrograms: Fine-grained Attribution with Executable ProgramsCode0
Improving Fairness of Large Language Models in Multi-document SummarizationCode0
ARC: Argument Representation and Coverage Analysis for Zero-Shot Long Document Summarization with Instruction Following LLMs—0
Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature SummarizationCode0
Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization—0
Document Attribution: Examining Citation Relationships using Large Language Models—0
A Unified Retrieval Framework with Document Ranking and EDU Filtering for Multi-document Summarization—0
Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document SummarizationCode0
Align to Structure: Aligning Large Language Models with Structural InformationCode0
M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?Code0
Can one size fit all?: Measuring Failure in Multi-Document Summarization Domain Transfer—0
Agent-Enhanced Large Language Models for Researching Political InstitutionsCode0
A Hybrid Architecture with Efficient Fine Tuning for Abstractive Patent Document Summarization—0
Mitigating Preference Hacking in Policy Optimization with Pessimism—0
Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processing—0
Show:102550
← PrevPage 2 of 16Next →
All datasetsCNN / Daily MailHowSumm-StepHowSumm-MethodArxiv HEP-TH citation grapharXiv Summarization DatasetBBC XSumWikiLingua (tr->en)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HAT-BARTROUGE-144.48—Unverified
2MatchSum (RoBERTa-base)ROUGE-144.41—Unverified
3Hie-BARTROUGE-144.35—Unverified
4MatchSum (BERT-base)ROUGE-144.22—Unverified
5BertSumExtROUGE-143.85—Unverified
6BigBird-PegasusROUGE-143.84—Unverified
7T5-11BROUGE-143.52—Unverified
8BERTSUM+TransformerROUGE-143.25—Unverified
9UniLM (Abstractive Summarization)ROUGE-143.08—Unverified
10Selector+Pointer GeneratorROUGE-141.72—Unverified
#ModelMetricClaimedVerifiedStatus
1LexRank (query: step title)ROUGE-139.6—Unverified
2CES (query: step title)ROUGE-139.3—Unverified
3CES (query: step + method titles)ROUGE-138.3—Unverified
4LexRank (query: step + method titles)ROUGE-138.2—Unverified
5CES (query: step + method + article titles)ROUGE-137—Unverified
6LexRank (query: step + method + article titles)ROUGE-136.3—Unverified
7GreedyRel (query: step + method titles)ROUGE-130.3—Unverified
8GreedyRel (query: step title)ROUGE-130.1—Unverified
9BM25-HierSumm (query: step + method titles)ROUGE-123—Unverified
10BM25-HierSumm (query: step title)ROUGE-122.3—Unverified
#ModelMetricClaimedVerifiedStatus
1LexRank (query: method + article + steps titles)ROUGE-153.5—Unverified
2CES (query: method + article + steps titles)ROUGE-152.2—Unverified
3GreedyRel (query: method + article + steps titles)ROUGE-148.6—Unverified
4CES (query: method title)ROUGE-148.4—Unverified
5CES (query: method + article titles)ROUGE-148.3—Unverified
6LexRank (query: method title)ROUGE-147.7—Unverified
7LexRank (query: method + article titles)ROUGE-147.1—Unverified
8GreedyRel (query: method title)ROUGE-143.4—Unverified
9GreedyRel (query: method + article titles)ROUGE-142.3—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepPyramidionROUGE-147.15—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepPyramidionRouge-219.99—Unverified
#ModelMetricClaimedVerifiedStatus
1BigBird-PegasusROUGE-147.12—Unverified
#ModelMetricClaimedVerifiedStatus
1DOCmT5Rouge-L31.37—Unverified