SKT5SciSumm - A Hybrid Generative Approach for Multi-Document Scientific Summarization

arXiv:2402.17311v1 Announce Type: new
Abstract: Summarization for scientific text has shown significant benefits both for the research community and human society. Given the fact that the nature of scientific text is distinctive and the input of the multi-document summarization task is substantially long, the task requires sufficient embedding generation and text truncation without losing important information. To tackle these issues, in this paper, we propose SKT5SciSumm - a hybrid framework for multi-document scientific summarization (MDSS). We leverage the Sentence-Transformer version …

abstract arxiv benefits community cs.cl document embedding generative human hybrid nature research research community society summarization text type