We introduce \emph{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
\emph{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.\footnote{Our code and data is available at
https://github.com/darsh10/Nutribullets.}

本文介绍了一种名为 Nutri-bullets 的多文档摘要任务，并提出了一种新的 extract-compose 模型来解决这个问题，然后使用策略网络显式选择多个摘要中的关键段落，最后通过特定语言模型进行摘要。结果比最先进的方法更加准确、相关和多样化。