# Nutribullets Hybrid: Multi-document Health Summarization

arXiv: https://arxiv.org/abs/2104.03465 · HTML: https://mlsanity.com/paper/2104.03465/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Enabling Language Models to Fill in the Blanks](https://mlsanity.com/paper/2005.05339/) (2020)
- [Neural Summarization by Extracting Sentences and Words](https://mlsanity.com/paper/1603.07252/) (2016)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [Generating Sentences by Editing Prototypes](https://mlsanity.com/paper/1709.08878/) (2017)
- [Learning Neural Templates for Text Generation](https://mlsanity.com/paper/1808.10122/) (2018)
- [Data-to-text Generation with Entity Modeling](https://mlsanity.com/paper/1906.03221/) (2019)
- [Blank Language Models](https://mlsanity.com/paper/2002.03079/) (2020)
- [Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization](https://mlsanity.com/paper/1808.06218/) (2018)
- [From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood](https://mlsanity.com/paper/1704.07926/) (2017)
- [Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models](https://mlsanity.com/paper/1801.07704/) (2018)
- [NCRF++: An Open-source Neural Sequence Labeling Toolkit](https://mlsanity.com/paper/1806.05626/) (2018)
- [Automatic Fact-guided Sentence Modification](https://mlsanity.com/paper/1909.13838/) (2019)
- [Informative and Controllable Opinion Summarization](https://mlsanity.com/paper/1909.02322/) (2019)
- [An Entity-Driven Framework for Abstractive Summarization](https://mlsanity.com/paper/1909.02059/) (2019)
- [Efficient Adaptation of Pretrained Transformers for Abstractive Summarization](https://mlsanity.com/paper/1906.00138/) (2019)
- [Concept Pointer Network for Abstractive Summarization](https://mlsanity.com/paper/1910.08486/) (2019)
- [Nutri-bullets: Summarizing Health Studies by Composing Segments](https://mlsanity.com/paper/2103.11921/) (2021)
- [Learning Features from Co-occurrences: A Theoretical Analysis](https://mlsanity.com/paper/1707.04218/) (2017)

## Built on by (most cited first, 3 of 3)

- [MS2: Multi-Document Summarization of Medical Studies](https://mlsanity.com/paper/2104.06486/) (2021)
- [What Would it Take to get Biomedical QA Systems into Practice?](https://mlsanity.com/paper/2109.10415/) (2021)
- [Generating Related Work](https://mlsanity.com/paper/2104.08668/) (2021)

## Abstract (arXiv)

We present a method for generating comparative summaries that highlights similarities and contradictions in input documents. The key challenge in creating such summaries is the lack of large parallel training data required for training typical summarization systems. To this end, we introduce a hybrid generation approach inspired by traditional concept-to-text systems. To enable accurate comparison between different sources, the model first learns to extract pertinent relations from input documents. The content planning component uses deterministic operators to aggregate these relations after identifying a subset for inclusion into a summary. The surface realization component lexicalizes this information using a text-infilling language model. By separately modeling content selection and realization, we can effectively train them with limited annotations. We implemented and tested the model in the domain of nutrition and health -- rife with inconsistencies. Compared to conventional methods, our framework leads to more faithful, relevant and aggregation-sensitive summarization -- while being equally fluent.