Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer

Hongyu Gong, Linfeng Song, Suma Bhat

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

4 Scopus citations

Abstract

Text style transfer aims to change an input sentence to an output sentence by changing its text style while preserving the content. Previous efforts on unsupervised text style transfer only use the surface features of words and sentences. As a result, the transferred sentences may either have inaccurate or missing information compared to the inputs. We address this issue by explicitly enriching the inputs via syntactic and semantic structures, from which richer features are then extracted to better capture the original information. Experiments on two text-style-transfer tasks show that our approach improves the content preservation of a strong unsupervised baseline model thereby demonstrating improved transfer performance.

Original languageEnglish (US)
Title of host publicationINLG 2020 - 13th International Conference on Natural Language Generation, Proceedings
EditorsBrian Davis, Yvette Graham, John Kelleher, Yaji Sripada
PublisherAssociation for Computational Linguistics (ACL)
Pages113-119
Number of pages7
ISBN (Electronic)9781952148545
StatePublished - 2020
Externally publishedYes
Event13th International Conference on Natural Language Generation, INLG 2020 - Virtual, Dublin, Ireland
Duration: Dec 15 2020Dec 18 2020

Publication series

NameINLG 2020 - 13th International Conference on Natural Language Generation, Proceedings

Conference

Conference13th International Conference on Natural Language Generation, INLG 2020
Country/TerritoryIreland
CityVirtual, Dublin
Period12/15/2012/18/20

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer'. Together they form a unique fingerprint.

Cite this