Extractive Research Slide Generation Using Windowed Labeling Ranking

Athar Sefid, Jian Wu, Prasenjit Mitra, C. Lee Giles

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

4 Scopus citations

Abstract

Presentation slides describing the content of scientific and technical papers are an efficient and effective way to present that work. However, manually generating presentation slides is labor intensive. We propose a method to automatically generate slides for scientific papers based on a corpus of 5000 paper-slide pairs compiled from conference proceedings websites. The sentence labeling module of our method is based on SummaRuNNer, a neural sequence model for extractive summarization. Instead of ranking sentences based on semantic similarities in the whole document, our algorithm measures importance and novelty of sentences by combining semantic and lexical features within a sentence window. Our method outperforms several baseline methods including SummaRuNNer by a significant margin in terms of ROUGE score.

Original languageEnglish (US)
Title of host publication2nd Workshop on Scholarly Document Processing, SDP 2021 - Proceedings of the Workshop
EditorsIz Beltagy, Arman Cohan, Guy Feigenblat, Dayne Freitag, Tirthankar Ghosal, Keith Hall, Drahomira Herrmannova, Petr Knoth, Kyle Lo, Philipp Mayr, Robert M. Patton, Michal Shmueli-Scheuer, Anita de Waard, Kuansan Wang, Lucy Lu Wang
PublisherAssociation for Computational Linguistics (ACL)
Pages91-96
Number of pages6
ISBN (Electronic)9781954085282
StatePublished - 2021
Event2nd Workshop on Scholarly Document Processing, SDP 2021 - Virtual, Online
Duration: Jun 10 2021 → …

Publication series

Name2nd Workshop on Scholarly Document Processing, SDP 2021 - Proceedings of the Workshop

Conference

Conference2nd Workshop on Scholarly Document Processing, SDP 2021
CityVirtual, Online
Period6/10/21 → …

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Extractive Research Slide Generation Using Windowed Labeling Ranking'. Together they form a unique fingerprint.

Cite this