Lune

EMNLP Findings2022

Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization

Dongmin Hyun, Xiting Wang, Chanyoung Park, Xing Xie, Hwanjo Yu

Abstract

Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. However, recent unsupervised models are extractive, which remove words from texts and thus they are less flexible than abstractive summarization. In this work, we devise an abstractive model based on reinforcement learning without ground-truth summaries. We formulate the unsupervised summarization based on the Markov decision process with rewards representing the summary quality. To further enhance the summary quality, we develop a multi-summary learning mechanism that generates multiple summaries with varying lengths for a given text, while making the summaries mutually enhance each other. Experimental results show that the proposed model substantially outperforms both abstractive and extractive models, yet frequently generating new words not contained in input texts.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Learning to summarize with human feedback cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
  • Leveraging Lead Bias for Zero-shot Abstractive News Summarization cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
  • Semi-Offline Reinforcement Learning for Optimized Text Generation cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Semi-Offline Reinforcement Learning for Optimized Text GenerationChangyu Chen, Xiting Wang, Yiqiao Jin, Victor Ye Dong et al.ICML 2023 · 18 citations

Builds on8

  1. PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationJingqing Zhang, Yao Zhao, Mohammad Saleh, Peter J. LiuICML 2020 · 2,453 citations
  2. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  3. Learning to summarize with human feedbackNisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel M. Ziegler et al.NeurIPS 2020 · 124 citations
  4. CTRLsum: Towards Generic Controllable Text SummarizationJunxian He, Wojciech Kryscinski, Bryan McCann, Nazneen Rajani et al.EMNLP 2022 · 59 citations
  5. Leveraging Lead Bias for Zero-shot Abstractive News SummarizationChenguang Zhu, Ziyi Yang, Robert Gmyr, Michael Zeng et al.SIGIR 2021 · 23 citations

Related papers

  1. Q-learning with Language Model for Edit-based Unsupervised SummarizationRyosuke Kohita, Akifumi Wachi, Yang Zhao, Ryuki TachibanaEMNLP 2020 · 2 citations
  2. MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision ProcessesNianlong Gu, Elliott Ash, Richard H. R. HahnloserACL 2022
  3. Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document SummarizationHanqi Jin, Tianming Wang, Xiaojun WanACL 2020 · 92 citations
  4. RepSum: Unsupervised Dialogue Summarization based on Replacement StrategyXiyan Fu, Yating Zhang, Tianyi Wang, Xiaozhong Liu et al.ACL 2021
  5. Factually Consistent Summarization via Reinforcement Learning with Textual Entailment FeedbackPaul Roit, Johan Ferret, Lior Shani, Roee Aharoni et al.ACL 2023 · 21 citations
Dusk over the sea between two cliffs drawn in fine vertical lines