The goal of text-to-text generation is to make machines express like a human in many
applications such as conversation, summarization, and translation. It is one of the most …

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

Prompting has shown impressive success in enabling large pretrained language models
(LMs) to perform diverse NLP tasks, especially when only few downstream data are …

As machine learning methods are deployed in real-world settings such as healthcare, legal
systems, and social science, it is crucial to recognize how they shape social biases and …

Deep supervised learning has achieved great success in the last decade. However, its
defects of heavy dependence on manual labels and vulnerability to attacks have driven …

Large transformer-based language models (LMs) trained on huge text corpora have shown
unparalleled generation capabilities. However, controlling attributes of the generated …

Recent text-to-image matching models apply contrastive learning to large corpora of
uncurated pairs of images and sentences. While such models can provide a powerful score …

Despite considerable advancements with deep neural language models, the enigma of
neural text degeneration persists when these models are tested as text generators. The …

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 …

Unsupervised image-to-image translation is an important and challenging problem in
computer vision. Given an image in the source domain, the goal is to learn the conditional …