Automatic generation of reviews of scientific papers
arXiv:2010.04147 · doi:10.1109/ICMLA51294.2020.00058
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.
arXiv commentAccepted as a full paper at ICMLA2020
References in corpus (5)
- Near linear time algorithm to detect community structures in large-scale networks
- SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
- Text mining and visualization using VOSviewer
- Neural Summarization by Extracting Sentences and Words
- Can Scientific Impact Be Predicted?