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 …
Same author or just same topic? towards content-independent style representations
Linguistic style is an integral component of language. Recent advances in the development
of style representations have increasingly used training objectives from authorship …
of style representations have increasingly used training objectives from authorship …
Exploring syntactic and semantic features for authorship attribution
H Wu, Z Zhang, Q Wu - Applied Soft Computing, 2021 - Elsevier
Authorship attribution is to extract features to identify authors of anonymous documents.
Many previous works on authorship attribution focus on statistical style features (eg …
Many previous works on authorship attribution focus on statistical style features (eg …
Authorship attribution of social media messages
The world is facing a new era in which social media communication plays a fundamental
role in people's lives. Along with proven benefits, several collateral drawbacks have risen …
role in people's lives. Along with proven benefits, several collateral drawbacks have risen …
Authorship attribution of late 19th century novels using GAN-BERT
Authorship attribution aims to identify the author of an anonymous text. The task becomes
even more worthwhile when it comes to literary works. For example, pen names were …
even more worthwhile when it comes to literary works. For example, pen names were …
Are you robert or roberta? deceiving online authorship attribution models using neural text generators
Recently, there has been a rise in the development of powerful pre-trained natural language
models, including GPT-2, Grover, and XLM. These models have shown state-of-the-art …
models, including GPT-2, Grover, and XLM. These models have shown state-of-the-art …
[HTML][HTML] Understanding writing style in social media with a supervised contrastively pre-trained transformer
Abstract We introduce the Style Transformer for Authorship Representations (STAR) to
detect and characterize writing style in social media. The model is trained on a …
detect and characterize writing style in social media. The model is trained on a …
Authorship attribution of microtext using capsule networks
Authorship attribution (AA) is an important task, as it identifies the author of a written text from
a set of suspect authors. Different methodologies of anonymous writing have been …
a set of suspect authors. Different methodologies of anonymous writing have been …
Weight of authorship evidence with multiple categories of stylometric features: A multinomial-based discrete model
S Ishihara - Science & Justice, 2023 - Elsevier
This study empirically demonstrates the efficacy of a two-level Dirichlet-multinomial
statistical model (the Multinomial system) for computing likelihood ratios (LR) for linguistic …
statistical model (the Multinomial system) for computing likelihood ratios (LR) for linguistic …
Defending Against Authorship Identification Attacks
H Wang - arXiv preprint arXiv:2310.01568, 2023 - arxiv.org
Authorship identification has proven unsettlingly effective in inferring the identity of the
author of an unsigned document, even when sensitive personal information has been …
author of an unsigned document, even when sensitive personal information has been …