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.
@article{arxiv.1905.07870,
title = {PaperRobot: Incremental Draft Generation of Scientific Ideas},
author = {Qingyun Wang and Lifu Huang and Zhiying Jiang and Kevin Knight and Heng Ji and Mohit Bansal and Yi Luan},
journal= {arXiv preprint arXiv:1905.07870},
year = {2020}
}
Comments
12 pages. Accepted by ACL 2019 Code and resource is available at https://github.com/EagleW/PaperRobot