Automatic generation of reviews of scientific papers

TL;DR

This paper introduces an automated method to generate scientific review papers by identifying key literature through bibliometric analysis and summarizing them with a BERT-based model, aiding researchers in exploring new fields efficiently.

Contribution

It presents a novel two-stage pipeline combining bibliometric analysis and BERT-based extractive summarization for automatic review generation.

Findings

Effective identification of key papers via bibliometric parameters.

Successful summarization of papers using BERT architecture.

Positive automatic and expert evaluation results.

Abstract

With an ever-increasing number of scientific papers published each year, it becomes more difficult for researchers to explore a field that they are not closely familiar with already. This greatly inhibits the potential for cross-disciplinary research. A traditional introduction into an area may come in the form of a review paper. However, not all areas and sub-areas have a current review. In this paper, we present a method for the automatic generation of a review paper corresponding to a user-defined query. This method consists of two main parts. The first part identifies key papers in the area by their bibliometric parameters, such as a graph of co-citations. The second stage uses a BERT based architecture that we train on existing reviews for extractive summarization of these key papers. We describe the general pipeline of our method and some implementation details and present both automatic and expert evaluations on the PubMed dataset.