A Study of Human Summaries of Scientific Articles
This addresses the problem of information overload for researchers and students by enhancing summarization tools, but it is incremental as it builds on existing methods.
The study analyzed human summaries from Shortscience.org to characterize them and apply insights to improve automatic summarization systems for scientific papers.
Researchers and students face an explosion of newly published papers which may be relevant to their work. This led to a trend of sharing human summaries of scientific papers. We analyze the summaries shared in one of these platforms Shortscience.org. The goal is to characterize human summaries of scientific papers, and use some of the insights obtained to improve and adapt existing automatic summarization systems to the domain of scientific papers.