DeepAI
Log In Sign Up

TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling

10/08/2020
by   Parker Riley, et al.
0

We present a novel approach to the problem of text style transfer. Unlike previous approaches that use parallel or non-parallel labeled data, our technique removes the need for labels entirely, relying instead on the implicit connection in style between adjacent sentences in unlabeled text. We show that T5 (Raffel et al., 2019), a strong pretrained text-to-text model, can be adapted to extract a style vector from arbitrary text and use this vector to condition the decoder to perform style transfer. As the resulting learned style vector space encodes many facets of textual style, we recast transfers as "targeted restyling" vector operations that adjust specific attributes of the input text while preserving others. When trained over unlabeled Amazon reviews data, our resulting TextSETTR model is competitive on sentiment transfer, even when given only four exemplars of each class. Furthermore, we demonstrate that a single model trained on unlabeled Common Crawl data is capable of transferring along multiple dimensions including dialect, emotiveness, formality, politeness, and sentiment.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/25/2019

Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer

Text style transfer is the task of transferring the style of text having...
05/26/2017

Style Transfer from Non-Parallel Text by Cross-Alignment

This paper focuses on style transfer on the basis of non-parallel text. ...
05/18/2021

LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer

Many types of text style transfer can be achieved with only small, preci...
06/03/2019

Massive Styles Transfer with Limited Labeled Data

Language style transfer has attracted more and more attention in the pas...
11/01/2018

Multiple-Attribute Text Style Transfer

The dominant approach to unsupervised "style transfer" in text is based ...
01/24/2023

Audience-Centric Natural Language Generation via Style Infusion

Adopting contextually appropriate, audience-tailored linguistic styles i...