PaperRobot: Incremental Draft Generation of Scientific Ideas

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.

arXiv comment12 pages. Accepted by ACL 2019 Code and resource is available at https://github.com/EagleW/PaperRobot

References in corpus (6)

• Neural Machine Translation by Jointly Learning to Align and Translate
• End-To-End Memory Networks
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Describing a Knowledge Base
• Neural Text Generation: A Practical Guide
• Paper Abstract Writing through Editing Mechanism

Cited by in corpus (11)

• A Survey of Knowledge-Enhanced Text Generation
• BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
• COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
• Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network
• ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
• Neural Language Generation: Formulation, Methods, and Evaluation
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
• Sentence-Permuted Paragraph Generation
• PatentMiner: Patent Vacancy Mining via Context-enhanced and Knowledge-guided Graph Attention
• SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation