PaperRobot: Incremental Draft Generation of Scientific Ideas
PaperRobot: Incremental Draft Generation of Scientific Ideas
复制标题
DOI：
10.18653/v1/p19-1191
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Qingyun Wang;Lifu Huang;Zhiying Jiang-;Kevin Knight;Heng Ji;Mohit Bansal;Yi Luan
中科院分区：
文献类型：
--
作者：
Qingyun Wang;Lifu Huang;Zhiying Jiang-;Kevin Knight;Heng Ji;Mohit Bansal;Yi Luan
我们提出了一个PaperRobot，它作为自动研究助理，通过（1）对目标领域的大量人类书面论文进行深入理解并构建全面的背景知识图（KG）;（2）通过预测链接来创造新想法背景知识图，结合图形注意力和上下文文本注意力;（3）基于记忆-注意力网络，逐步写出一篇新论文的一些关键要素：从输入标题沿着预测的相关实体生成论文摘要，从摘要生成结论和未来工作，最后，从未来的工作中产生一个标题，为后续的文件。图灵测试要求生物医学领域专家比较系统输出和人类编写的字符串，显示PaperRobot生成的摘要，结论和未来的工作部分，并且选择新标题而不是人类编写的标题的比例分别高达30%，24%和12%。
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.