Text style transfer: A review and experimental evaluation

Z Hu, RKW Lee, CC Aggarwal, A Zhang - ACM SIGKDD Explorations …, 2022 - dl.acm.org
The stylistic properties of text have intrigued computational linguistics researchers in recent
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 …

Mind the style of text! adversarial and backdoor attacks based on text style transfer

F Qi, Y Chen, X Zhang, M Li, Z Liu, M Sun - arxiv preprint arxiv …, 2021 - arxiv.org
Adversarial attacks and backdoor attacks are two common security threats that hang over
deep learning. Both of them harness task-irrelevant features of data in their implementation …

Disentangled representation learning for non-parallel text style transfer

V John, L Mou, H Bahuleyan, O Vechtomova - arxiv preprint arxiv …, 2018 - arxiv.org
This paper tackles the problem of disentangling the latent variables of style and content in
language models. We propose a simple yet effective approach, which incorporates auxiliary …

Style transformer: Unpaired text style transfer without disentangled latent representation

N Dai, J Liang, X Qiu, X Huang - arxiv preprint arxiv:1905.05621, 2019 - arxiv.org
Disentangling the content and style in the latent space is prevalent in unpaired text style
transfer. However, two major issues exist in most of the current neural models. 1) It is difficult …

Multiple-attribute text rewriting

G Lample, S Subramanian, E Smith… - International …, 2019 - openreview.net
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'' …

Transforming delete, retrieve, generate approach for controlled text style transfer

A Sudhakar, B Upadhyay, A Maheswaran - arxiv preprint arxiv …, 2019 - arxiv.org
Text style transfer is the task of transferring the style of text having certain stylistic attributes,
while preserving non-stylistic or content information. In this work we introduce the …

Controlled hallucinations: Learning to generate faithfully from noisy data

K Filippova - arxiv preprint arxiv:2010.05873, 2020 - arxiv.org
Neural text generation (data-or text-to-text) demonstrates remarkable performance when
training data is abundant which for many applications is not the case. To collect a large …

A novel estimator of mutual information for learning to disentangle textual representations

P Colombo, C Clavel, P Piantanida - arxiv preprint arxiv:2105.02685, 2021 - arxiv.org
Learning disentangled representations of textual data is essential for many natural language
tasks such as fair classification, style transfer and sentence generation, among others. The …

Expertise style transfer: A new task towards better communication between experts and laymen

Y Cao, R Shui, L Pan, MY Kan, Z Liu… - arxiv preprint arxiv …, 2020 - arxiv.org
The curse of knowledge can impede communication between experts and laymen. We
propose a new task of expertise style transfer and contribute a manually annotated dataset …