mlsanityData to 7 Oct 2026

Analyzing Sentence Fusion in Abstractive Summarization

arXiv 1910.00203 ↗First posted 1 Oct 2019cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 6; 2023: 2; 2024: 3; 2025: 0; 2026: 1.

19 papers.

Sort:

  1. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  2. 2024Attribute First, then Generate: Locally-attributable Grounded Text Generationcited by 54
  3. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  4. 2022Learning to Revise References for Faithful Summarizationcited by 28
  5. 2021QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositionscited by 16
  6. 2021Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarizationcited by 15
  7. 2021StreamHover: Livestream Transcript Summarization and Annotationcited by 15
  8. 2021A Sliding-Window Approach to Automatic Creation of Meeting Minutescited by 14
  9. 2023A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarizationcited by 14
  10. 2021A New Approach to Overgenerating and Scoring Abstractive Summariescited by 13
  11. 2024A Modular Approach for Multimodal Summarization of TV Showscited by 13
  12. 2021Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attributioncited by 10
7 more
  1. 2022Controlled Text Reductioncited by 10
  2. 2022Leveraging Locality in Abstractive Text Summarizationcited by 9
  3. 2022Towards Summary Candidates Fusioncited by 8
  4. 2022How "Multi" is Multi-Document Summarization?cited by 8
  5. 2023What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarizationcited by 8
  6. 2024Source Identification in Abstractive Summarizationcited by 2
  7. 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?cited by 0