相关论文: Knowing False Negatives: An Adversarial Training M…

The noisy labeling problem has been one of the major obstacles for distant supervised relation extraction. Existing approaches usually consider that the noisy sentences are useless and will harm the model's performance. Therefore, they…

In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…

Deep Learning (DL) has shown potential in accelerating Magnetic Resonance Image acquisition and reconstruction. Nevertheless, there is a dearth of tailored methods to guarantee that the reconstruction of small features is achieved with high…

GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem. We focus on the discriminator, which…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Knowledge graphs (KGs) are typically incomplete and we often wish to infer new facts given the existing ones. This can be thought of as a binary classification problem; we aim to predict if new facts are true or false. Unfortunately, we…

We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-level relation mentions given only proposition-level…

State-of-the-art models for relation extraction (RE) in the biomedical domain consider finetuning BioBERT using classification, but they may suffer from the anisotropy problem. Contrastive learning methods can reduce this anisotropy…

Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention. Self-supervised learning followed by the supervised fine-tuning on a few labeled examples can…

Positive unlabeled learning is a binary classification problem with positive and unlabeled data. It is common in domains where negative labels are costly or impossible to obtain, e.g., medicine and personalized advertising. Most approaches…

The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used…

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…

In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is…

Detecting negatives (such as non-entailment relationships, unanswerable questions, and false claims) is an important and challenging aspect of many natural language understanding tasks. Though manually collecting challenging negative…

In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, excluding the anchor. However, this approach can result in the creation of negative pairs…

Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…

Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples. In this paper, we present a novel training procedure and a thresholding test strategy, towards robust…

Continual Relation Extraction (CRE) aims to continually learn new emerging relations while avoiding catastrophic forgetting. Existing CRE methods mainly use memory replay and contrastive learning to mitigate catastrophic forgetting.…

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…

A principal barrier to training temporal relation extraction models in new domains is the lack of varied, high quality examples and the challenge of collecting more. We present a method of automatically collecting distantly-supervised…