Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at scientific conferences. We hypothesize that such talks constitute a coherent and concise description of the papers' content, and can form the basis for good summaries. We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries. A model trained on this dataset achieves similar performance as models trained on a dataset of summaries created manually. In addition, we validated the quality of our summaries by human experts.
@article{arxiv.1906.01351,
title = {TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks},
author = {Guy Lev and Michal Shmueli-Scheuer and Jonathan Herzig and Achiya Jerbi and David Konopnicki},
journal= {arXiv preprint arXiv:1906.01351},
year = {2019}
}