相关论文: Contrastive Learning with Hard Negative Entities f…

Emotion recognition in conversations (ERC) is a rapidly evolving task within the natural language processing community, which aims to detect the emotions expressed by speakers during a conversation. Recently, a growing number of ERC methods…

Contrastive learning is a method of learning visual representations by training Deep Neural Networks (DNNs) to increase the similarity between representations of positive pairs (transformations of the same image) and reduce the similarity…

Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive learning only…

Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data. Previous analyses of such approaches have largely focused on individual…

Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation. Learning the implicit structured representations of entity names without context and external knowledge…

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of…

Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To…

Recently, using large pretrained Transformer models for transfer learning tasks has evolved to the point where they have become one of the flagship trends in the Natural Language Processing (NLP) community, giving rise to various outlooks…

This work models named entity distribution from a way of visualizing topological structure of embedding space, so that we make an assumption that most, if not all, named entities (NEs) for a language tend to aggregate together to be…

Recognizing similarities among entities is central to both human cognition and computational intelligence. Within this broader landscape, Entity Set Expansion is one prominent task aimed at taking an initial set of (tuples of) entities and…

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often…

Entity disambiguation (ED) is the last step of entity linking (EL), when candidate entities are reranked according to the context they appear in. All datasets for training and evaluating models for EL consist of convenience samples, such as…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and…

Entity matching is the problem of identifying which records refer to the same real-world entity. It has been actively researched for decades, and a variety of different approaches have been developed. Even today, it remains a challenging…

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…

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting…

Learning from Multi-Positive and Unlabeled (MPU) data has gradually attracted significant attention from practical applications. Unfortunately, the risk of MPU also suffer from the shift of minimum risk, particularly when the models are…

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…