相关论文: CoNT: Contrastive Neural Text Generation

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several…

Today's most accurate language models are trained on orders of magnitude more language data than human language learners receive - but with no supervision from other sensory modalities that play a crucial role in human learning. Can we make…

Chain of thought (CoT) has proven useful for problems requiring complex reasoning. Many of these problems are both textual and multimodal. Given the inputs in different modalities, a model generates a rationale and then uses it to answer a…

Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels…

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…

The output of text-to-image synthesis systems should be coherent, clear, photo-realistic scenes with high semantic fidelity to their conditioned text descriptions. Our Cross-Modal Contrastive Generative Adversarial Network (XMC-GAN)…

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…

Computed Tomography Report Generation (CTRG) aims to automate the clinical radiology reporting process, thereby reducing the workload of report writing and facilitating patient care. While deep learning approaches have achieved remarkable…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful…

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…

In many task settings, text classification models are likely to encounter examples from novel classes on which they cannot predict correctly. Selective prediction, in which models abstain on low-confidence examples, provides a possible…

Contrastive learning has been applied successfully to learn vector representations of text. Previous research demonstrated that learning high-quality representations benefits from batch-wise contrastive loss with a large number of…

In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies \cite{li-etal-2020-multi-encoder} have shown that the context encoder generates noise and…

Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs for…

Trapped by the label scarcity in molecular property prediction and drug design, graph contrastive learning (GCL) came forward. Leading contrastive learning works show two kinds of view generators, that is, random or learnable data…

Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Generative Adversarial Networks (GANs) have shown great promise recently in image generation. Training GANs for language generation has proven to be more difficult, because of the non-differentiable nature of generating text with recurrent…

Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against these attacks, most existing methods apply adversarial training…