mlsanityData to 7 Oct 2026

Nutri-bullets: Summarizing Health Studies by Composing Segments

arXiv 2103.11921 ↗First posted 22 Mar 2021cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce Nutri-bullets, a multi-document summarization task for health and nutrition. First, we present two datasets of food and health summaries from multiple scientific studies. Furthermore, we propose a novel extract-compose model to solve the problem in the regime of limited parallel data. We explicitly select key spans from several abstracts using a policy network, followed by composing the selected spans to present a summary via a task specific language model. Compared to state-of-the-art methods, our approach leads to more faithful, relevant and diverse summarization -- properties imperative to this application. For instance, on the BreastCancer dataset our approach gets a more than 50% improvement on relevance and faithfulness.footnoteOur code and data is available at urlhttps://github.com/darsh10/Nutribullets.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

43 of 61 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2016Pointer Sentinel Mixture Modelscited by 2,992
  6. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  7. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  8. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  9. 2015Teaching Machines to Read and Comprehendcited by 1,039
  10. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  11. 2019Text Summarization with Pretrained Encoderscited by 553
  12. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
31 more
  1. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  2. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
  3. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  4. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  5. 2016Rationalizing Neural Predictionscited by 281
  6. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
  7. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
  8. 2019Text Generation from Knowledge Graphs with Graph Transformerscited by 122
  9. 2016Neural Summarization by Extracting Sentences and Wordscited by 114
  10. 2018A Study of Reinforcement Learning for Neural Machine Translationcited by 74
  11. 2018Multi-Reward Reinforced Summarization with Saliency and Entailmentcited by 73
  12. 2019Leveraging BERT for Extractive Text Summarization on Lecturescited by 63
  13. 2019Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answeringcited by 63
  14. 2018Deriving Machine Attention from Human Rationalescited by 54
  15. 2019Data-to-text Generation with Entity Modelingcited by 45
  16. 2018Toward Abstractive Summarization Using Semantic Representationscited by 43
  17. 2020Blank Language Modelscited by 43
  18. 2018Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarizationcited by 42
  19. 2019Answer-based Adversarial Training for Generating Clarification Questionscited by 42
  20. 2018Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Modelscited by 39
  21. 2018Deep Reinforcement Learning For Sequence to Sequence Modelscited by 39
  22. 2018NCRF++: An Open-source Neural Sequence Labeling Toolkitcited by 29
  23. 2019DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusioncited by 29
  24. 2019Automatic Fact-guided Sentence Modificationcited by 28
  25. 2019Informative and Controllable Opinion Summarizationcited by 27
  26. 2019An Entity-Driven Framework for Abstractive Summarizationcited by 25
  27. 2017Split and Rephrasecited by 24
  28. 2019Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learningcited by 19
  29. 2019Efficient Adaptation of Pretrained Transformers for Abstractive Summarizationcited by 13
  30. 2019Concept Pointer Network for Abstractive Summarizationcited by 13
  31. 2014Generating Extractive Summaries of Scientific Paradigmscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 1; 2024: 2.

6 papers.

  1. 2021The Factual Inconsistency Problem in Abstractive Text Summarization: A Surveycited by 79
  2. 2022A Survey on Medical Document Summarizationcited by 14
  3. 2024Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: A Benchmark Studycited by 13
  4. 2023Do Multi-Document Summarization Models Synthesize?cited by 11
  5. 2021Nutribullets Hybrid: Multi-document Health Summarizationcited by 3
  6. 2024Survey on Abstractive Text Summarization: Dataset, Models, and Metricscited by 1