分类:PaperRobot: Incremental Draft Generation of Scientific Ideas

来自Big Physics
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.


Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan, PaperRobot: Incremental Draft Generation of Scientific Ideas, arXiv:1905.07870


Abstract

We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper. Turing Tests, where a biomedical domain expert is asked to compare a system output and a human-authored string, show PaperRobot generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time, respectively.

总结和评论

这篇文章[1]实现了一个能够提出来研究论文的idea的机器人,并且还可以产生论文的一部分(背景介绍、问题定位)。其主要思路是:从现有论文和知识库中体现出来概念地图或者说知识地图——其主要包含概念和概念关系;然后,从概念地图中做链路预测,找到可能可以进一步研究的概念之间的联系。最后,按照这个联系还有概念地图、知识背景来创作文章,把真正的研究部分交给研究者来完成。

其中,最重要的技术就是概念和概念之间关系的提取。

进一步研究

实际上,这个概念和概念之间关系提取的技术可以用于任何知识或者篇章的结构化图形化网络化表示。有了这个网络表示以后,我们可以把不同的篇章聚合起来成为知识框架,从而更好地定位每一项研究工作。当然,科学家确实可以以这个概念地图为基础来决定下一步的研究问题。同事,我们可以做更好的基于文章内容的科研评价。老师和学生可以在这个概念地图上做更好的教和学。

同时,这个技术还可能可以帮助自然语言处理技术更好地理解自然语言,甚至用于篇章的阅读分级等其他任务。

参考文献

  1. Qingyun Wang, Lifu Huang, Zhiying Jiang, Kevin Knight, Heng Ji, Mohit Bansal, Yi Luan, PaperRobot: Incremental Draft Generation of Scientific Ideas, arXiv:1905.07870. https://arxiv.org/abs/1905.07870

本分类目前不含有任何页面或媒体文件。