相关论文: Contrastive Learning with Adversarial Perturbation…

Contrastive Learning has recently achieved state-of-the-art performance in a wide range of tasks. Many contrastive learning approaches use mined hard negatives to make batches more informative during training but these approaches are…

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…

As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to…

Recently, generative adversarial networks have gained a lot of popularity for image generation tasks. However, such models are associated with complex learning mechanisms and demand very large relevant datasets. This work borrows concepts…

In recent years, short Text Matching tasks have been widely applied in the fields ofadvertising search and recommendation. The difficulty lies in the lack of semantic information and word ambiguity caused by the short length of the text.…

Triple extraction is an essential task in information extraction for natural language processing and knowledge graph construction. In this paper, we revisit the end-to-end triple extraction task for sequence generation. Since generative…

Despite advances in generating fluent texts, existing pretraining models tend to attach incoherent event sequences to involved entities when generating narratives such as stories and news. We conjecture that such issues result from…

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an…

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…

Domain-specific variants of contrastive learning can construct positive pairs from two distinct in-domain images, while traditional methods just augment the same image twice. For example, we can form a positive pair from two satellite…

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 text, (ii) solely rely on cross-entropy loss that leads to issues like…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…

Story Ending Generation (SEG) is a challenging task in natural language generation. Recently, methods based on Pre-trained Language Models (PLM) have achieved great prosperity, which can produce fluent and coherent story endings. However,…

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is…

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, where given a notion of semantic similarity, the learner tries…