Text style transfer: A review and experimental evaluation
The stylistic properties of text have intrigued computational linguistics researchers in recent
years. Specifically, researchers have investigated the text style transfer task (TST), which …
years. Specifically, researchers have investigated the text style transfer task (TST), which …
A review of text style transfer using deep learning
M Toshevska, S Gievska - IEEE Transactions on Artificial …, 2021 - ieeexplore.ieee.org
Style is an integral component of a sentence indicated by the choice of words a person
makes. Different people have different ways of expressing themselves; however, they adjust …
makes. Different people have different ways of expressing themselves; however, they adjust …
Multiple-attribute text rewriting
The dominant approach to unsupervised" style transfer''in text is based on the idea of
learning a latent representation, which is independent of the attributes specifying its" style'' …
learning a latent representation, which is independent of the attributes specifying its" style'' …
Multiple-attribute text style transfer
The dominant approach to unsupervised" style transfer" in text is based on the idea of
learning a latent representation, which is independent of the attributes specifying its" style" …
learning a latent representation, which is independent of the attributes specifying its" style" …
Meet your favorite character: Open-domain chatbot mimicking fictional characters with only a few utterances
In this paper, we consider mimicking fictional characters as a promising direction for building
engaging conversation models. To this end, we present a new practical task where only a …
engaging conversation models. To this end, we present a new practical task where only a …
TextSETTR: Few-shot text style extraction and tunable targeted restyling
We present a novel approach to the problem of text style transfer. Unlike previous
approaches requiring style-labeled training data, our method makes use of readily-available …
approaches requiring style-labeled training data, our method makes use of readily-available …
Semi-supervised text style transfer: Cross projection in latent space
Text style transfer task requires the model to transfer a sentence of one style to another style
while retaining its original content meaning, which is a challenging problem that has long …
while retaining its original content meaning, which is a challenging problem that has long …
Self-supervised text style transfer using cycle-consistent adversarial networks
Text Style Transfer (TST) is a relevant branch of natural language processing that aims to
control the style attributes of a piece of text while preserving its original content. To address …
control the style attributes of a piece of text while preserving its original content. To address …
Generative pretraining for paraphrase evaluation
We introduce ParaBLEU, a paraphrase representation learning model and evaluation metric
for text generation. Unlike previous approaches, ParaBLEU learns to understand …
for text generation. Unlike previous approaches, ParaBLEU learns to understand …
A dataset for low-resource stylized sequence-to-sequence generation
Low-resource stylized sequence-to-sequence (S2S) generation is in high demand.
However, its development is hindered by the datasets which have limitations on scale and …
However, its development is hindered by the datasets which have limitations on scale and …