Browse State-of-the-Art › Sentence Compression

Sentence Compression

22 papers with code · 1 benchmark · 2 datasets archive 2025-07-28

Natural Language Processing

Sentence Compression is the task of reducing the length of text by removing non-essential content while preserving important facts and grammaticality.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 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.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Google Dataset (6 rows) SLAHAN (LSTM+syntactic-information) Syntactically Look-Ahead Attention Network for Sentence Compression 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

2 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: 149 · with a code link: 22 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 149 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 149, 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 May 2018 4 repositories listed
    We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations.
  • 1 Jun 2013 2 repositories listed
  • We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors…
  • 26 May 2022 1 repository listed
    We advance the state-of-the-art in unsupervised abstractive dialogue summarization by utilizing multi-sentence compression graphs.
  • 17 May 2022 1 repository listed
    Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality.
  • 16 Oct 2021 1 repository listed
    By exploiting the property of NDD, we implement a unsupervised and even training-free algorithm for extractive sentence compression.
  • 4 Oct 2021 1 repository listed
    Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation.
  • 16 Feb 2021 1 repository listed
    In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
  • 22 Jan 2021 1 repository listed
    Reliable evaluation protocols are of utmost importance for reproducible NLP research.
  • 1 Jul 2020 1 repository listed
    The compressor masks the input, and the reconstructor tries to regenerate it.
  • 4 Feb 2020 1 repository listed
    Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words.
  • 27 Dec 2019 1 repository listed
    In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT.
  • 1 Jun 2019 1 repository listed
    The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
  • 7 Apr 2019 1 repository listed
    The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
  • 1 Oct 2018 1 repository listed
    In this paper we advocate the use of bilingual corpora which are abundantly available for training sentence compression models.
  • 7 Sep 2018 1 repository listed
    In sentence compression, the task of shortening sentences while retaining the original meaning, models tend to be trained on large corpora containing pairs of verbose and compressed sentences.
  • 1 Jul 2018 1 repository listed
    In this paper, we present a sequence-to-sequence based approach for mapping natural language sentences to AMR semantic graphs.
  • 1 Jul 2018 1 repository listed
    Automatic abstractive summary generation remains a significant open problem for natural language processing.
  • 1 Nov 2017 1 repository listed
    Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification…
  • 1 Sep 2017 1 repository listed
    We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research.
  • 31 Mar 2017 1 repository listed
    Sentence simplification aims to make sentences easier to read and understand.
  • 19 Mar 2016 1 repository listed
    Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models.
  • Tiny Transformers Excel at Sentence Compression
    30 Oct 2024 0 repositories listed
    It is staggering that words of the English language, which are on average represented by 5--6 bytes of ASCII, require as much as 24 kilobytes when served to large language models.
  • Target-Aware Language Modeling via Granular Data Sampling
    23 Sep 2024 0 repositories listed
    Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources.
  • InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models
    16 Jun 2024 0 repositories listed
    Extractive summarization can produce faithful summaries but often requires additional constraints such as a desired summary length.
  • AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
    30 May 2024 0 repositories listed
    Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective.
  • From Lengthy to Lucid: A Systematic Literature Review on NLP Techniques for Taming Long Sentences
    8 Dec 2023 0 repositories listed
    Long sentences have been a persistent issue in written communication for many years since they make it challenging for readers to grasp the main points or follow the initial intention of the writer.
  • Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts
    13 May 2023 0 repositories listed
    Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content.
  • A Simple Yet Effective Corpus Construction Method for Chinese Sentence Compression
    1 Jun 2022 0 repositories listed
    Deletion-based sentence compression in the English language has made significant progress over the past few decades.
  • SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map
    1 Nov 2021 0 repositories listed
    Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English.
  • Leveraging Information Bottleneck for Scientific Document Summarization
    4 Oct 2021 0 repositories listed
  • Cross-Register Projection for Headline Part of Speech Tagging
    15 Sep 2021 0 repositories listed
  • RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy
    1 Aug 2021 0 repositories listed
  • Etat de l’art en compression multi-phrases pour la synthèse de documents (State-of-the-art of multi-sentence compression for document summarization)
    1 Jun 2021 0 repositories listed
  • With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms
    25 Jan 2021 0 repositories listed
  • Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
    15 Oct 2020 0 repositories listed
  • A Token-wise CNN-based Method for Sentence Compression
    23 Sep 2020 0 repositories listed
  • Automatic Speech Summarisation: A Scoping Review
    27 Aug 2020 0 repositories listed
  • Sentence Compression as Deletion with Contextual Embeddings
    5 Jun 2020 0 repositories listed
  • Analyse de la régulation de la longueur dans un système neuronal de compression de phrase : une étude du modèle LenInit (Investigating Length Regulation in a Sentence Compression Neural System : a Study on the LenInit Model)
    1 Jun 2020 0 repositories listed
  • Combining Word Embeddings and N-grams for Unsupervised Document Summarization
    25 Apr 2020 0 repositories listed
  • A Multilingual Study of Multi-Sentence Compression using Word Vertex-Labeled Graphs and Integer Linear Programming
    9 Apr 2020 0 repositories listed
  • Machine Translation with Unsupervised Length-Constraints
    7 Apr 2020 0 repositories listed
  • A Difference-of-Convex Programming Approach With Parallel Branch-and-Bound For Sentence Compression Via A Hybrid Extractive Model
    2 Feb 2020 0 repositories listed
  • Cross-Task Knowledge Transfer for Query-Based Text Summarization
    1 Nov 2019 0 repositories listed
  • Query-focused Sentence Compression in Linear Time
    1 Nov 2019 0 repositories listed
  • Towards Annotating and Creating Summary Highlights at Sub-sentence Level
    1 Nov 2019 0 repositories listed
  • Towards Annotating and Creating Sub-Sentence Summary Highlights
    17 Oct 2019 0 repositories listed
  • Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression
    7 Sep 2019 0 repositories listed
  • Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study
    1 Jul 2019 0 repositories listed
  • Unsupervised Rewriter for Multi-Sentence Compression
    1 Jul 2019 0 repositories listed
  • Query-focused Sentence Compression in Linear Time
    19 Apr 2019 0 repositories listed
  • Sentence Compression via DC Programming Approach
    13 Feb 2019 0 repositories listed
  • Human acceptability judgements for extractive sentence compression
    1 Feb 2019 0 repositories listed
  • When does deep multi-task learning work for loosely related document classification tasks?
    1 Nov 2018 0 repositories listed
  • Generating Syntactic Paraphrases
    1 Oct 2018 0 repositories listed
  • SALSA-TEXT : self attentive latent space based adversarial text generation
    28 Sep 2018 0 repositories listed
  • Text Summarization as Tree Transduction by Top-Down TreeLSTM
    24 Sep 2018 0 repositories listed
  • Adversarial Neural Networks for Cross-lingual Sequence Tagging
    14 Aug 2018 0 repositories listed
  • Abstractive Unsupervised Multi-Document Summarization using Paraphrastic Sentence Fusion
    1 Aug 2018 0 repositories listed
  • An Operation Network for Abstractive Sentence Compression
    1 Aug 2018 0 repositories listed
  • 1 Jul 2018 0 repositories listed
  • Deep Learning Approaches to Text Production
    1 Jun 2018 0 repositories listed
  • 1 Jun 2018 0 repositories listed
  • Multi-Sentence Compression with Word Vertex-Labeled Graphs and Integer Linear Programming
    1 Jun 2018 0 repositories listed
  • A New Annotated Portuguese/Spanish Corpus for the Multi-Sentence Compression Task
    1 May 2018 0 repositories listed
  • SumeCzech: Large Czech News-Based Summarization Dataset
    1 May 2018 0 repositories listed
  • Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging
    1 Nov 2017 0 repositories listed
  • An Eye-tracking Study of Named Entity Annotation
    1 Sep 2017 0 repositories listed
  • Cascaded Attention based Unsupervised Information Distillation for Compressive Summarization
    1 Sep 2017 0 repositories listed
  • Identifying Semantic Edit Intentions from Revisions in Wikipedia
    1 Sep 2017 0 repositories listed
  • Tackling Biomedical Text Summarization: OAQA at BioASQ 5B
    1 Aug 2017 0 repositories listed
  • Self-organized Hierarchical Softmax
    26 Jul 2017 0 repositories listed
  • 1 Jul 2017 0 repositories listed
  • Japanese Sentence Compression with a Large Training Dataset
    1 Jul 2017 0 repositories listed
  • Oracle Summaries of Compressive Summarization
    1 Jul 2017 0 repositories listed
  • Crowd-Sourced Iterative Annotation for Narrative Summarization Corpora
    1 Apr 2017 0 repositories listed
  • Metaheuristic Approaches to Lexical Substitution and Simplification
    1 Apr 2017 0 repositories listed
  • A Proposition-Based Abstractive Summariser
    1 Dec 2016 0 repositories listed
  • Cross-lingual Transfer of Correlations between Parts of Speech and Gaze Features
    1 Dec 2016 0 repositories listed
  • Neural Clinical Paraphrase Generation with Attention
    1 Dec 2016 0 repositories listed
  • Parallel Sentence Compression
    1 Dec 2016 0 repositories listed
  • Predicting sentential semantic compatibility for aggregation in text-to-text generation
    1 Dec 2016 0 repositories listed
  • Using Relevant Public Posts to Enhance News Article Summarization
    1 Dec 2016 0 repositories listed
  • A Dataset and Evaluation Metrics for Abstractive Compression of Sentences and Short Paragraphs
    1 Nov 2016 0 repositories listed
  • Language as a Latent Variable: Discrete Generative Models for Sentence Compression
    23 Sep 2016 0 repositories listed
  • Multi-document abstractive summarization using ILP based multi-sentence compression
    22 Sep 2016 0 repositories listed
  • Abstractive Compression of Captions with Attentive Recurrent Neural Networks
    1 Sep 2016 0 repositories listed
  • Annotating and Predicting Non-Restrictive Noun Phrase Modifications
    1 Aug 2016 0 repositories listed
  • Extracting token-level signals of syntactic processing from fMRI - with an application to PoS induction
    1 Aug 2016 0 repositories listed
  • MUSEEC: A Multilingual Text Summarization Tool
    1 Aug 2016 0 repositories listed
  • Phrase Generalization: a Corpus Study in Multi-Document Abstracts and Original News Alignments
    1 Aug 2016 0 repositories listed
  • Text Simplification as Tree Labeling
    1 Aug 2016 0 repositories listed
  • A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
    24 Jun 2016 0 repositories listed
  • CoastalCPH at SemEval-2016 Task 11: The importance of designing your Neural Networks right
    1 Jun 2016 0 repositories listed
  • On Improving Informativity and Grammaticality for Multi-Sentence Compression
    7 May 2016 0 repositories listed
  • 12 Apr 2016 0 repositories listed
  • Fast k-best Sentence Compression
    28 Oct 2015 0 repositories listed
  • Abstractive Multi-document Summarization with Semantic Information Extraction
    1 Sep 2015 0 repositories listed
  • Phrase-based Compressive Cross-Language Summarization
    1 Sep 2015 0 repositories listed

Syntology lines on 1 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