Automatic Synonym and Phrase Replacement Shows Promise for Style Transformation

Authorship
Foaad Khosmood and Robert Levinson
Publication
IEEE International Conference of Machine Learning and Applications
Conference
Location
Washington, DC
Abstract

Style transformation refers to the process by which a piece of text written in a certain style of writing is transformed into another text exhibiting a distinctly different style of writing without significant change to the meaning of individual sentences. In this paper we continue investigation into the linguistic style transformation problem and demonstrate current achievements in transformation on sample texts from a standard authorship attribution corpus.