SlideGen: An abstractive section-based slide generator for scholarly documents

Athar Sefid, Prasenjit Mitra, Lee Giles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

Presentation slides generated from research papers provide summary of the papers primarily to guide talks. Manually generating presentation slides is labor intensive. We propose a method to automatically generate slides for scientific articles based on a corpus of 5000 paper-slide pairs compiled from conference proceedings websites which is the largest dataset used for scholarly article summarization. We generate slides 1) extractively by selecting salient sentences from the paper and 2) abstractively by fine-tuning pre-trained language models to learn the language of slides. The results show the superiority of the extractive models in terms of ROUGE scores. However, abstractive summaries are less verbose and follow the language of the slides by generating phrases rather than full sentences.

Original languageEnglish (US)
Title of host publicationDocEng 2021 - Proceedings of the 2021 ACM Symposium on Document Engineering
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450385961
DOIs
StatePublished - Aug 16 2021
Event21st ACM Symposium on Document Engineering, DocEng 2021 - Virtual, Online, Ireland
Duration: Aug 24 2021Aug 27 2021

Publication series

NameDocEng 2021 - Proceedings of the 2021 ACM Symposium on Document Engineering

Conference

Conference21st ACM Symposium on Document Engineering, DocEng 2021
Country/TerritoryIreland
CityVirtual, Online
Period8/24/218/27/21

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'SlideGen: An abstractive section-based slide generator for scholarly documents'. Together they form a unique fingerprint.

Cite this