mlsanityData to 14 Oct 2026

Content Selection in Deep Learning Models of Summarization

arXiv 1810.12343 ↗First posted 29 Oct 2018cs.CLcited by 64

Not on the map. Why?

Abstract (arXiv)

We carry out experiments with deep learning models of summarization across the domains of news, personal stories, meetings, and medical articles in order to understand how content selection is performed. We find that many sophisticated features of state of the art extractive summarizers do not improve performance over simpler models. These results suggest that it is easier to create a summarizer for a new domain than previous work suggests and bring into question the benefit of deep learning models for summarization for those domains that do have massive datasets (i.e., news). At the same time, they suggest important questions for new research in summarization; namely, new forms of sentence representations or external knowledge sources are needed that are better suited to the summarization task.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 27; 2022: 19; 2023: 7; 2024: 5; 2025: 2; 2026: 4.

64 papers.

Sort:

By area:

  1. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
  2. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  3. 2021BookSum: A Collection of Datasets for Long-form Narrative Summarizationcited by 184
  4. 2022BRIO: Bringing Order to Abstractive Summarizationcited by 161
  5. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 155
  6. 2023Unlimiformer: Long-Range Transformers with Unlimited Length Inputcited by 128
  7. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 108
  8. 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
  9. 2021Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarizationcited by 51
  10. 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
  11. 2021Controllable Neural Dialogue Summarization with Personal Named Entity Planningcited by 36
  12. 2021What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarizationcited by 35
38 more
  1. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  2. 2022Toward Unifying Text Segmentation and Long Document Summarizationcited by 28
  3. 2021RefSum: Refactoring Neural Summarizationcited by 25
  4. 2022Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluationcited by 24
  5. 2021Unsupervised Extractive Summarization using Pointwise Mutual Informationcited by 23
  6. 2022EntSUM: A Data Set for Entity-Centric Summarizationcited by 22
  7. 2023A Survey on Out-of-Distribution Evaluation of Neural NLP Modelscited by 20
  8. 2021TODSum: Task-Oriented Dialogue Summarization with State Trackingcited by 19
  9. 2023A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understandingcited by 18
  10. 2023VCSUM: A Versatile Chinese Meeting Summarization Datasetcited by 18
  11. 2021A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regionscited by 17
  12. 2021End-to-End Segmentation-based News Summarizationcited by 16
  13. 2021StreamHover: Livestream Transcript Summarization and Annotationcited by 15
  14. 2021A Sliding-Window Approach to Automatic Creation of Meeting Minutescited by 14
  15. 2022A Survey on Medical Document Summarizationcited by 14
  16. 2021SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarizationcited by 13
  17. 2021Demoting the Lead Bias in News Summarization via Alternating Adversarial Learningcited by 10
  18. 2021Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attributioncited by 10
  19. 2021TLDR9+: A Large Scale Resource for Extreme Summarization of Social Media Postscited by 10
  20. 2022Read Top News First: A Document Reordering Approach for Multi-Document News Summarizationcited by 9
  21. 2023Generating EDU Extracts for Plan-Guided Summary Re-Rankingcited by 9
  22. 2024Hierarchical Indexing for Retrieval-Augmented Opinion Summarizationcited by 7
  23. 2022NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarizationcited by 5
  24. 2021Summary Explorer: Visualizing the State of the Art in Text Summarizationcited by 4
  25. 2024Understanding Position Bias Effects on Fairness in Social Multi-Document Summarizationcited by 4
  26. 2024Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarizationcited by 4
  27. 2022Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injectioncited by 3
  28. 2022Sequence-Based Extractive Summarisation for Scientific Articlescited by 3
  29. 2025NUTSHELL: A Dataset for Abstract Generation from Scientific Talkscited by 3
  30. 2026When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisationcited by 2
  31. 2026Measuring Alignment With Reader Highlights Net of Position and Lengthcited by 2
  32. 2021Unsupervised Extractive Summarization by Human Memory Simulationcited by 1
  33. 2021Analysis of GraphSum's Attention Weights to Improve the Explainability of Multi-Document Summarizationcited by 1
  34. 2022Text Summarization with Oracle Expectationcited by 1
  35. 2024Self-Supervised Position Debiasing for Large Language Modelscited by 1
  36. 2021SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysiscited by 0
  37. 2021VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Searchcited by 0
  38. 2021Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generationcited by 0

50 most cited of 64 All 64 (JSON)