Generating Extractive Summaries of Scientific Paradigms
Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. The authors' goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. They show how they can use citations to produce automatically generated, readily consumable, technical extractive summaries. They first propose C-LexRank, a model for summarizing single scientific paper based on citations, which employs community detection and extracts salient information-rich sentences. Next, they further extend their experiments to summarize a set of papers, which cover the same scientific topic.