mlsanityData to 14 Oct 2026

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

arXiv 2205.14522 ↗First posted 28 May 2022cs.CL cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE score, which is the main evaluation metric for summarization, whereas controlling the summary length has not drawn much attention. In our work, we address a new problem of explicit character-level length control for summarization, and propose a dynamic programming algorithm based on the Connectionist Temporal Classification (CTC) model. Results show that our approach not only achieves higher ROUGE scores but also yields more complete sentences.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

28 of 51 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  3. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
  4. 2017Non-Autoregressive Neural Machine Translationcited by 463
  5. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 396
  6. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 365
  7. 2018Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinementcited by 195
  8. 2018Bottom-Up Abstractive Summarizationcited by 177
  9. 2020Non-Autoregressive Machine Translation with Latent Alignmentscited by 96
  10. 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 94
  11. 2019Fast Structured Decoding for Sequence Modelscited by 59
  12. 2019Positional Encoding to Control Output Sequence Lengthcited by 56
16 more
  1. 2018BanditSum: Extractive Summarization as a Contextual Banditcited by 46
  2. 2021Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervisioncited by 40
  3. 2019BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principlecited by 39
  4. 2019Neural Extractive Text Summarization with Syntactic Compressioncited by 37
  5. 2020Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignmentcited by 37
  6. 2021Non-Autoregressive Text Generation with Pre-trained Language Modelscited by 36
  7. 2020BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretrainingcited by 33
  8. 2020TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoisingcited by 30
  9. 2019SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compressioncited by 27
  10. 2021RefSum: Refactoring Neural Summarizationcited by 25
  11. 2020SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compressioncited by 24
  12. 2020Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extractioncited by 23
  13. 2019Jointly Extracting and Compressing Documents with Summary State Representationscited by 12
  14. 2018Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networkscited by 11
  15. 2020Length-controllable Abstractive Summarization by Guiding with Summary Prototypecited by 9
  16. 2020Cascaded Text Generation with Markov Transformerscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 8; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024Counting Ability of Large Language Models and Impact of Tokenizationcited by 32
  2. 2025Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMscited by 31
  3. 2025TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysiscited by 22
  4. 2023Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Surveycited by 18
  5. 2025Multi2: Multi-Agent Test-Time Scalable Framework for Multi-Document Processingcited by 12
  6. 2025PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMscited by 11
  7. 2024Supervised Chain of Thoughtcited by 5
  8. 2025Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencingcited by 5
  9. 2025Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencingcited by 4
  10. 2025Multilingual Non-Autoregressive Machine Translation without Knowledge Distillationcited by 1
  11. 2025Bidirectional Representations Augmented Autoregressive Biological Sequence Generationcited by 1
  12. 2023From Lengthy to Lucid: A Systematic Literature Review on NLP Techniques for Taming Long Sentencescited by 0
1 more
  1. 2026Agent Memory with Episodic Retrieval for Financial Decision-Makingcited by 0