Generating Extractive Summaries of Scientific Paradigms
This addresses the need for researchers and scientists to efficiently digest scientific content, though it is incremental as it builds on existing bibliometric and summarization techniques.
The paper tackles the problem of quickly understanding large technical material by generating extractive summaries of scientific literature using citations, showing that citations provide unique information for creating summaries of single articles and sets of papers on topics like Question Answering and Dependency Parsing.
Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.