mlsanityData to 14 Oct 2026

Global Encoding for Abstractive Summarization

arXiv 1805.03989 ↗First posted 10 May 2018cs.CL cs.AI cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

In neural abstractive summarization, the conventional sequence-to-sequence (seq2seq) model often suffers from repetition and semantic irrelevance. To tackle the problem, we propose a global encoding framework, which controls the information flow from the encoder to the decoder based on the global information of the source context. It consists of a convolutional gated unit to perform global encoding to improve the representations of the source-side information. Evaluations on the LCSTS and the English Gigaword both demonstrate that our model outperforms the baseline models, and the analysis shows that our model is capable of reducing repetition.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 3; 2023: 6; 2024: 1; 2025: 1.

16 papers.

Sort:

  1. 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 102
  2. 2023An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPTcited by 57
  3. 2021ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generationcited by 31
  4. 2022Towards Improving Faithfulness in Abstractive Summarizationcited by 27
  5. 2021Word Graph Guided Summarization for Radiology Findingscited by 19
  6. 2023Explicit Syntactic Guidance for Neural Text Generationcited by 8
  7. 2023An Analysis of Abstractive Text Summarization Using Pre-trained Modelscited by 7
  8. 2022WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from Paragraphscited by 6
  9. 2022Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-Endcited by 6
  10. 2023Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Ordercited by 6
  11. 2021IOT: Instance-wise Layer Reordering for Transformer Structurescited by 5
  12. 2023Abstractive Text Summarization using Attentive GRU based Encoder-Decodercited by 2
4 more
  1. 2021Neural Abstractive Unsupervised Summarization of Online News Discussionscited by 1
  2. 2021Towards Controlled and Diverse Generation of Article Commentscited by 0
  3. 2023StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generationcited by 0
  4. 2025Hierarchical Multi-Label Generation with Probabilistic Level-Constraintcited by 0