相关论文: Denoising Distant Supervision for Relation Extract…

Deep neural networks have exhibited impressive performance in image classification tasks but remain vulnerable to adversarial examples. Standard adversarial training enhances robustness but typically fails to explicitly address inter-class…

Modern deep neural networks (DNNs) become frail when the datasets contain noisy (incorrect) class labels. Robust techniques in the presence of noisy labels can be categorized into two folds: developing noise-robust functions or using…

In many applications labeled data is not readily available, and needs to be collected via pain-staking human supervision. We propose a rule-exemplar method for collecting human supervision to combine the efficiency of rules with the quality…

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Relation extraction in the biomedical domain is a challenging task due to a lack of labeled data and a long-tail distribution of fact triples. Many works leverage distant supervision which automatically generates labeled data by pairing a…

We develop a framework for estimating unknown partial differential equations from noisy data, using a deep learning approach. Given noisy samples of a solution to an unknown PDE, our method interpolates the samples using a neural network,…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a…

Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in…

Relation extraction (RE) models have been challenged by their reliance on training data with expensive annotations. Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context,…

Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation. In this paper, we propose an attention-based deep residual network to directly learn a mapping…

Recent relation extraction (RE) works have shown encouraging improvements by conducting contrastive learning on silver labels generated by distant supervision before fine-tuning on gold labels. Existing methods typically assume all these…

We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were…

Unsupervised relation extraction (URE) aims at discovering underlying relations between named entity pairs from open-domain plain text without prior information on relational distribution. Existing URE models utilizing contrastive learning,…

Distantly supervised named entity recognition (DS-NER) has emerged as a cheap and convenient alternative to traditional human annotation methods, enabling the automatic generation of training data by aligning text with external resources.…

Multiple instance learning (MIL) has become the standard learning paradigm for distantly supervised relation extraction (DSRE). However, due to relation extraction being performed at bag level, MIL has significant hardware requirements for…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…

Generalizing from limited data is particularly critical for models in domains such as material science, where task-relevant features in experimental datasets are often heavily confounded by measurement noise and experimental artifacts.…

In this paper, we introduced the novel concept of advisor network to address the problem of noisy labels in image classification. Deep neural networks (DNN) are prone to performance reduction and overfitting problems on training data with…