Summarization with Precise Length Control

Many applications of text generation such as summarization benefit from accurately controlling the text length. Existing approaches on length-controlled summarization either result in degraded performance or can only control the length approximately. In this work, we present a framework to generate summaries with precisely the specified number of tokens or sentences, while maintaining or even improving the text quality. In addition, we jointly train the models to predict the lengths, so our model can generate summaries with optimal length. We evaluate the proposed framework on the CNNDM dataset and show improved performance compared to existing methods.

• Publication year

  2023

• Venue

  arXiv.org

• Publication date

  2023-05-09

• Fields of study

  Computer Science

• Identifiers
  DOI 10.48550/arXiv.2305.05171arXiv 2305.05171
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization

  2022cited by this paper
• Length Control in Abstractive Summarization by Pretraining Information Selection

  2022cited by this paper
• Controllable Summarization with Constrained Markov Decision Process

  2021cited by this paper
• LenAtten: An Effective Length Controlling Unit For Text Summarization

  2021cited by this paper
• Length-controllable Abstractive Summarization by Guiding with Summary Prototype

  2020cited by this paper
• DeBERTa: Decoding-enhanced BERT with Disentangled Attention

  2020cited by this paper
• CTRLsum: Towards Generic Controllable Text Summarization

  2020influential reference
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

  2019cited by this paper
• Positional Encoding to Control Output Sequence Length

  2019cited by this paper
• Global Optimization under Length Constraint for Neural Text Summarization

  2019cited by this paper
• A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

  2018influential reference
• Controlling Length in Abstractive Summarization Using a Convolutional Neural Network

  2018cited by this paper
• Controllable Abstractive Summarization

  2017influential reference
• Controlling Output Length in Neural Encoder-Decoders

  2016cited by this paper
• Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond

  2016cited by this paper

• Controlling Summarization Length Through EOS Token Weighting

  2025cites this paper
• Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs

  2025cites this paper
• TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation

  2024cites this paper
• Length Controllable Model for Images and Texts Summarization

  2024cites this paper