PaperRobot: Incremental Draft Generation of Scientific Ideas
This addresses the challenge of accelerating scientific research by automating idea generation and drafting for researchers, though it is incremental in combining existing techniques like graph attention and memory networks.
The paper tackles the problem of automating scientific idea generation and paper drafting by introducing PaperRobot, which constructs knowledge graphs from existing papers, predicts new ideas, and incrementally writes key paper sections. The result shows that in Turing Tests, generated abstracts, conclusions, and titles were chosen over human-written ones up to 30%, 24%, and 12% of the time, respectively.
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.