Unpaired abstract-to-conclusion text style transfer using CycleGANs

Haotong Wang, Yves Lepage, Chooi Ling Goh

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

Abstract

The availability of paired examples greatly facilitates the task of style transfer by allowing the use of supervised learning. However, our scenario does not enjoy such a condition. We focus on style transfer for academic writing, and examine the possibility of performing style transfer between sentences from the abstract and conclusion sections of a scientific article in the Natural Language Processing field, in both directions. We assume a latent correlation between the abstract and conclusion styles, and construct an unpaired data set. We propose the use of a version of CydeGAN based on transformers to perform the task. Our approach is shown to realize differences in tense or word usage which are characteristic of the different sections.

Original languageEnglish
Title of host publication2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages435-440
Number of pages6
ISBN (Electronic)9781728192796
DOIs
Publication statusPublished - 2020 Oct 17
Event12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020 - Virtual, Depok, Indonesia
Duration: 2020 Oct 172020 Oct 18

Publication series

Name2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020

Conference

Conference12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020
Country/TerritoryIndonesia
CityVirtual, Depok
Period20/10/1720/10/18

Keywords

  • GANs
  • Text style transfer
  • Unpaired data

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Unpaired abstract-to-conclusion text style transfer using CycleGANs'. Together they form a unique fingerprint.

Cite this