# PaperRobot: Incremental Draft Generation of Scientific Ideas

## TL;DR

PaperRobot is an AI system that autonomously understands scientific literature, generates new research ideas by predicting connections in knowledge graphs, and incrementally writes key sections of a scientific paper, outperforming humans in some Turing Tests.

## Contribution

The paper introduces a novel AI system that combines knowledge graph reasoning and attention mechanisms to generate scientific paper components incrementally, advancing research automation.

## Key findings

- Generated sections are often preferred over human-written ones in Turing Tests.
- System successfully predicts meaningful links in scientific knowledge graphs.
- Achieves up to 30% success rate in fooling biomedical experts.

## 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.