Nutri-Bullets: Summarizing Health Studies by Composing Segments
Abstract
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.
Cite
Text
Shah et al. "Nutri-Bullets: Summarizing Health Studies by Composing Segments." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I15.17624Markdown
[Shah et al. "Nutri-Bullets: Summarizing Health Studies by Composing Segments." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/shah2021aaai-nutri/) doi:10.1609/AAAI.V35I15.17624BibTeX
@inproceedings{shah2021aaai-nutri,
title = {{Nutri-Bullets: Summarizing Health Studies by Composing Segments}},
author = {Shah, Darsh J. and Yu, Lili and Lei, Tao and Barzilay, Regina},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {13780-13788},
doi = {10.1609/AAAI.V35I15.17624},
url = {https://mlanthology.org/aaai/2021/shah2021aaai-nutri/}
}