Automatic generation of reviews of scientific papers
This addresses the challenge for researchers in accessing cross-disciplinary knowledge, though it is incremental as it builds on existing techniques like BERT and bibliometrics.
The paper tackles the problem of researchers struggling to explore unfamiliar scientific fields due to the high volume of publications by developing a method to automatically generate review papers based on user queries, achieving results evaluated on the PubMed dataset.
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.