MSˆ2: Multi-Document Summarization of Medical Studies
MSˆ2: Multi-Document Summarization of Medical Studies
复制标题
DOI：
10.18653/v1/2021.emnlp-main.594
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Jay DeYoung;Iz Beltagy;Madeleine van Zuylen;Bailey Kuehl;Lucy Lu Wang
中科院分区：
文献类型：
--
作者：
Jay DeYoung;Iz Beltagy;Madeleine van Zuylen;Bailey Kuehl;Lucy Lu Wang
为了评估任何医疗干预措施的有效性，研究人员必须进行时间密集的人工文献综述。NLP系统可以帮助自动化或协助这个昂贵的过程的一部分。为了支持这一目标，我们发布了MS 1002（医学研究的多文档摘要），这是一个包含超过470K文档和20K摘要的数据集，来自科学文献。该数据集促进了可以评估和汇总多项研究中相互矛盾的证据的系统的开发，并且是生物医学领域第一个大规模的公开可用的多文档摘要数据集。我们实验了一个基于BART的摘要系统，早期的结果很有希望，但仍有重要的工作要做，以达到更高的摘要质量。我们制定我们的摘要输入和目标在自由文本和结构化的形式，并修改最近提出的指标，以评估我们的系统生成的摘要的质量。数据和模型可在https://github.com/allenai/ms2上查阅。
To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support of this goal, we release MSˆ2 (Multi-Document Summarization of Medical Studies), a dataset of over 470k documents and 20K summaries derived from the scientific literature. This dataset facilitates the development of systems that can assess and aggregate contradictory evidence across multiple studies, and is the first large-scale, publicly available multi-document summarization dataset in the biomedical domain. We experiment with a summarization system based on BART, with promising early results, though significant work remains to achieve higher summarization quality. We formulate our summarization inputs and targets in both free text and structured forms and modify a recently proposed metric to assess the quality of our system’s generated summaries. Data and models are available at https://github.com/allenai/ms2.