Browse State-of-the-Art › Extractive Text Summarization
Extractive Text Summarization
34 papers with code · 5 benchmarks · 5 datasets archive 2025-07-28
Given a document, selecting a subset of the words or sentences which best represents a summary of the document.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CNN / Daily Mail (15 rows) | HAHSum | Neural Extractive Summarization with Hierarchical Attentive... | — | — | Compare |
| DebateSum (3 rows) | Longformer-Base | DebateSum: A large-scale argument mining and summarization dataset | code | Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified | Compare |
| GovReport (2 rows) | MemSum (extractive) | MemSum: Extractive Summarization of Long Documents Using... | code | — | Compare |
| DUC 2004 Task 1 (1 row) | Abs | A Neural Attention Model for Abstractive Sentence Summarization | code | — | Compare |
| DUC 2004 (1 row) | Pre-training-meets-Clustering-A-Hybrid-Extractive-Multi-Document-Summarization-Model | Pre-training Meets Clustering: A Hybrid Extractive Multi-document... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
5 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 95 · with a code link: 34 · where Syntology ran a sample: 7 (6 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (7 of 95 tagged: 6 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 95 of 95, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
14 Apr 2017 39 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 30 ran (of which 11 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 2 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 34 unverified (of 64 harvested samples) · 44 pointer-only (licence)Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text).
-
22 Aug 2019 19 repositories listed Syntology community repositories only · 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified (of 21 harvested samples) · 5 pointer-only (licence)For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained…
-
4 Dec 2018 14 repositories listed Syntology community repositories only · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 1 pointer-only (licence)Dot-product attention has wide applications in computer vision and natural language processing.
-
25 Mar 2019 12 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks.
-
7 Jun 2019 8 repositories listedThis paper reports on the project called Lecture Summarization Service, a python based RESTful service that utilizes the BERT model for text embeddings and KMeans clustering to identify sentences closes to the centroid…
-
2 Sep 2015 4 repositories listedSummarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build.
-
14 Nov 2020 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Finally, we present a search engine for this dataset which is utilized extensively by members of the National Speech and Debate Association today.
-
13 Apr 2020 3 repositories listedRedundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step.
-
13 Mar 2023 2 repositories listedThe goal of multimodal summarization is to extract the most important information from different modalities to form output summaries.
-
7 Dec 2020 2 repositories listedCompetitive Debate's increasingly technical nature has left competitors looking for tools to accelerate evidence production.
-
27 Apr 2020 2 repositories listedMost general-purpose extractive summarization models are trained on news articles, which are short and present all important information upfront.
-
19 Apr 2020 2 repositories listedThis paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
-
8 Jul 2019 2 repositories listedThe recent years have seen remarkable success in the use of deep neural networks on text summarization.
-
20 Feb 2018 2 repositories listedDetecting novelty of an entire document is an Artificial Intelligence (AI) frontier problem that has widespread NLP applications, such as extractive document summarization, tracking development of news events…
-
1 Apr 2017 2 repositories listedThe textual similarity is a crucial aspect for many extractive text summarization methods.
-
26 Nov 2024 1 repository listedHere, we propose a novel Word pair-based Gaussian Sentence Similarity (WGSS) algorithm for calculating the semantic relation between two sentences.
-
25 May 2023 1 repository listedOutcomes validate that our proposed model shows greatly enhanced performance as compared to the existent unsupervised state-of-the-art approaches.
-
1 Oct 2022 1 repository listedIn this paper, we develop a Graph-Based Unsupervised Summarization(GUSUM) method for extractive text summarization based on the principle of including the most important sentences while excluding sentences with similar…
-
1 Oct 2022 1 repository listedIn this paper, we describe the first IDN dataset (IDN-Sum) designed specifically for training and testing IDN text summarization algorithms.
-
19 Jul 2021 1 repository listedWe introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at each step with information on the current extraction history.
-
16 Oct 2020 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)We also find in experiments that our model is less dependent on sentence positions.
-
26 Apr 2020 1 repository listedAn intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships.
-
4 Dec 2019 1 repository listedMulti-document summarization is more challenging than single-document summarization since it has to solve the problem of overlapping information among sentences from different documents.
-
1 Nov 2019 1 repository listedIn this work, we re-examine the problem of extractive text summarization for long documents.
-
30 Oct 2019 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples) · 1 pointer-only (licence)Recently BERT has been adopted for document encoding in state-of-the-art text summarization models.
-
16 Jul 2019 1 repository listedOur method creates an extractive summary by selecting the sentences with the closest embeddings to the document embedding.
-
3 Feb 2019 1 repository listedIn this work, we present a neural model for single-document summarization based on joint extraction and syntactic compression.
-
6 Nov 2018 1 repository listedWe propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization.
-
27 Sep 2018 1 repository listedIn this paper, we introduce Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization, inspired by the observation that it is often necessary for a human to read an…
-
25 Sep 2018 1 repository listedIn this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.
-
6 Jul 2018 1 repository listed
-
1 Jul 2018 1 repository listed
-
23 Feb 2018 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
1 Sep 2017 1 repository listed
-
28 Aug 2024 0 repositories listed
-
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches10 Jul 2024 0 repositories listed
-
RankSum An unsupervised extractive text summarization based on rank fusion7 Feb 2024 0 repositories listed
-
Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization16 Nov 2023 0 repositories listed
-
CovSumm: an unsupervised transformer-cum-graph-based hybrid document summarization model for CORD-1926 Apr 2023 0 repositories listed
-
San-BERT: Extractive Summarization for Sanskrit Documents using BERT and it's variants4 Apr 2023 0 repositories listed
-
Efficient Informed Proposals for Discrete Distributions via Newton's Series Approximation27 Feb 2023 0 repositories listed
-
Extractive Text Summarization Using Generalized Additive Models with Interactions for Sentence Selection21 Dec 2022 0 repositories listed
-
Multi Perspective Scientific Document Summarization With Graph Attention Networks (GATS)1 Oct 2022 0 repositories listed
-
Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization28 Apr 2022 0 repositories listed
-
17 Mar 2022 0 repositories listed
-
Extractive Text Summarization with Latent Topics using Heterogeneous Graph Neural Network16 Jan 2022 0 repositories listed
-
GUSUM: Graph-Based Unsupervised Summarization using Sentence-BERT and Sentence Features16 Jan 2022 0 repositories listed
-
A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods6 Dec 2021 0 repositories listed
-
HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information16 Nov 2021 0 repositories listed
-
A Hybrid PSO-GA for Extractive Text Summarization1 Nov 2021 0 repositories listed
-
1 Nov 2021 0 repositories listed
-
Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization1 Nov 2021 0 repositories listed
-
Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization31 Aug 2021 0 repositories listed
-
Multiplex Graph Neural Network for Extractive Text Summarization29 Aug 2021 0 repositories listed
-
Jointly Learning Salience and Redundancy by Adaptive Sentence Reranking for Extractive Summarization1 Aug 2021 0 repositories listed
-
Topic Modeling Based Extractive Text Summarization29 Jun 2021 0 repositories listed
-
Knowledge Graph and Deep Neural Network for Extractive Text Summarization by Utilizing Triples1 Dec 2020 0 repositories listed
-
1 Nov 2020 0 repositories listed
-
Improving Neural Text Summarization using Knowledge Graphs24 Oct 2020 0 repositories listed
-
Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks13 Oct 2020 0 repositories listed
-
MultiGBS: A multi-layer graph approach to biomedical summarization27 Aug 2020 0 repositories listed
-
Abstractive Text Summarization for Sanskrit Prose: A Study of Methods and Approaches1 May 2020 0 repositories listed
-
Towards a Reliable and Robust Methodology for Crowd-Based Subjective Quality Assessment of Query-Based Extractive Text Summarization1 May 2020 0 repositories listed
-
Combining Word Embeddings and N-grams for Unsupervised Document Summarization25 Apr 2020 0 repositories listed
-
Probabilistic Model of Narratives Over Topical Trends in Social Media: A Discrete Time Model14 Apr 2020 0 repositories listed
-
At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization6 Apr 2020 0 repositories listed
-
Hybrid MemNet for Extractive Summarization25 Dec 2019 0 repositories listed
-
Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization25 Dec 2019 0 repositories listed
-
Towards Supervised Extractive Text Summarization via RNN-based Sequence Classification13 Nov 2019 0 repositories listed
-
Towards automatic extractive text summarization of A-133 Single Audit reports with machine learning8 Nov 2019 0 repositories listed
-
19 Sep 2019 0 repositories listed
-
A study of semantic augmentation of word embeddings for extractive summarization1 Sep 2019 0 repositories listed
-
A topic-based sentence representation for extractive text summarization1 Sep 2019 0 repositories listed
-
Exploring Domain Shift in Extractive Text Summarization30 Aug 2019 0 repositories listed
-
Learning with fuzzy hypergraphs: a topical approach to query-oriented text summarization22 Jun 2019 0 repositories listed
-
A Novel System for Extractive Clinical Note Summarization using EHR Data1 Jun 2019 0 repositories listed
-
16 May 2019 0 repositories listed
-
Language Model Pre-training for Hierarchical Document Representations26 Jan 2019 0 repositories listed
-
BoWLer: A neural approach to extractive text summarization1 Dec 2018 0 repositories listed
-
Abstractive Text-Image Summarization Using Multi-Modal Attentional Hierarchical RNN1 Oct 2018 0 repositories listed
-
22 Aug 2018 0 repositories listed
-
Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks20 Jul 2018 0 repositories listed
-
20 May 2018 0 repositories listed
-
Using Statistical and Semantic Models for Multi-Document Summarization11 May 2018 0 repositories listed
-
Extractive Text Summarization using Neural Networks27 Feb 2018 0 repositories listed
-
Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization1 Sep 2017 0 repositories listed
-
Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization25 Aug 2017 0 repositories listed
-
Extractive Multi Document Summarization using Dynamical Measurements of Complex Networks5 Aug 2017 0 repositories listed
-
A New Persian Text Summarization Approach Based on Natural Language Processing and Graph Similarity1 Feb 2017 0 repositories listed
-
Classify or Select: Neural Architectures for Extractive Document Summarization14 Nov 2016 0 repositories listed
-
A Dynamic Programming Algorithm for Tree Trimming-based Text Summarization1 May 2015 0 repositories listed
-
Multi-layered graph-based multi-document summarization model17 May 2014 0 repositories listed
-
Using Supervised Bigram-based ILP for Extractive Summarization1 Aug 2013 0 repositories listed
-
Using Document Summarization Techniques for Speech Data Subset Selection1 Jun 2013 0 repositories listed
-
Twitter Topic Summarization by Ranking Tweets using Social Influence and Content Quality1 Dec 2012 0 repositories listed
Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections