Nutri-bullets: Summarizing Health Studies by Composing Segments

Authors

  • Darsh J Shah Massachusetts Institute of Technology
  • Lili Yu Asapp Inc.
  • Tao Lei ASAPP Inc.
  • Regina Barzilay Massachusetts Institute of Technology

Keywords:

Applications

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.

Downloads

Published

2021-05-18

How to Cite

Shah, D. J., Yu, L., Lei, T., & Barzilay, R. (2021). Nutri-bullets: Summarizing Health Studies by Composing Segments. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13780-13788. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17624

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II