Suppr超能文献

RevManHAL:迈向系统评价中的自动文本生成

RevManHAL: towards automatic text generation in systematic reviews.

作者信息

Torres Torres Mercedes, Adams Clive E

机构信息

Computer Vision Lab, University of Nottingham, Nottingham, UK.

Cochrane Schizophrenia Group, Institute of Mental Health, University of Nottingham, Triumph Road, Nottingham, NG7 2TU, UK.

出版信息

Syst Rev. 2017 Feb 9;6(1):27. doi: 10.1186/s13643-017-0421-y.

Abstract

BACKGROUND

Systematic reviews are a key part of healthcare evaluation. They involve important painstaking but repetitive work. A major producer of systematic reviews, the Cochrane Collaboration, employs Review Manager (RevMan) programme-a software which assists reviewers and produces XML-structured files. This paper describes an add-on programme (RevManHAL) which helps auto-generate the abstract, results and discussion sections of RevMan-generated reviews in multiple languages. The paper also describes future developments for RevManHAL.

METHODS

RevManHAL was created in Java using NetBeans by a programmer working full time for 2 months.

RESULTS

The resulting open-source programme uses editable phrase banks to envelop text/numbers from within the prepared RevMan file in formatted readable text of a chosen language. In this way, considerable parts of the review's 'abstract', 'results' and 'discussion' sections are created and a phrase added to 'acknowledgements'.

CONCLUSION

RevManHAL's output needs to be checked by reviewers, but already, from our experience within the Cochrane Schizophrenia Group (200 maintained reviews, 900 reviewers), RevManHAL has saved much time which is better employed thinking about the meaning of the data rather than restating them. Many more functions will become possible as review writing becomes increasingly automated.

摘要

背景

系统评价是医疗保健评估的关键部分。它们涉及重要但繁琐且重复的工作。系统评价的主要产出者Cochrane协作网使用Review Manager(RevMan)程序——一种协助评价者并生成XML结构文件的软件。本文描述了一个附加程序(RevManHAL),它有助于自动生成RevMan生成的多种语言评价的摘要、结果和讨论部分。本文还描述了RevManHAL的未来发展。

方法

RevManHAL由一名全职工作两个月的程序员使用NetBeans在Java中创建。

结果

生成的开源程序使用可编辑的短语库,将准备好的RevMan文件中的文本/数字包装成所选语言的格式化可读文本。通过这种方式,创建了评价的“摘要”、“结果”和“讨论”部分的相当一部分,并在“致谢”中添加了一个短语。

结论

RevManHAL的输出需要由评价者进行检查,但根据我们在Cochrane精神分裂症小组的经验(200篇持续评价,900名评价者),RevManHAL已经节省了大量时间,这些时间更好地用于思考数据的意义而不是重述数据。随着评价撰写越来越自动化,更多功能将成为可能。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/53d3/5301442/01ed2f422d30/13643_2017_421_Fig1_HTML.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验