The stylistic properties of text have intrigued computational linguistics researchers in recent
years. Specifically, researchers have investigated the text style transfer task (TST), which …

Text style transfer is an important task in natural language generation, which aims to control
certain attributes in the generated text, such as politeness, emotion, humor, and many …

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 …

Natural question generation (QG) aims to generate questions from a passage and an
answer. Previous works on QG either (i) ignore the rich structure information hidden in …

Training learnable metrics using modern language models has recently emerged as a
promising method for the automatic evaluation of machine translation. However, existing …

Neural controllable text generation is an important area gaining attention due to its plethora
of applications. Although there is a large body of prior work in controllable text generation …

Scarcity of parallel data causes formality style transfer models to have scarce success in
preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to …

We take the first step towards multilingual style transfer by creating and releasing
XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian …

Text style transfer pursues altering the style of a sentence while remaining its main content
unchanged. Due to the lack of parallel corpora, most recent work focuses on unsupervised …

Steering language generation towards objectives or away from undesired content has been
a long-standing goal in utilizing language models (LM). Recent work has demonstrated …