Scientific Documents Collection and Summarization for Survey Writing

Abstract

In the process of survey writing, searching for scientific documents related to a topic and fully understanding these documents are two critical but time-consuming steps. Automatic paper collection and summarization technologies can help to improve work efficiency and work quality. Therefore, this work-in-progress paper integrates the citation recommendation model, the structured content extraction model, and the long scientific documents summarization model to propose an automatic scientific document collection and summarization system. This system can extract topics from single or multiple paragraphs, collect relevant papers, and generate a summary table for the collected papers to benefit survey writing.