The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …

Code generation aims to synthesize code and fulfill functional requirements based on
natural language (NL) specifications, which can greatly improve development efficiency. In …

Most existing methods that cope with noisy labels usually assume that the classwise data
distributions are well balanced. They are difficult to deal with the practical scenarios where …

Real-world large-scale datasets are both noisily labeled and class-imbalanced. The issues
seriously hurt the generalization of trained models. It is hence significant to address the …

In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited
due to the under-representation of tail samples. Class rebalancing, information …

Background: Achieving endoscopic and histological remission is a critical treatment
objective in ulcerative colitis (UC). Nevertheless, interobserver variability can significantly …

Learning with imbalanced data is a challenging problem in deep learning. Over-sampling is
a widely used technique to re-balance the sampling distribution of training data. However …

Data biases such as class imbalance and label noise always exist in large-scale datasets in
real-world. These problems bring huge challenges to deep learning methods. Some …

Recently, deep learning (DL) presents a promising performance in the joint classification of
multimodal remote sensing (RS) data. However, most of the approaches adopt a supervised …

Dialogue discourse parsing is a fundamental natural language processing task. It can
benefit a series of conversation-related downstream tasks including dialogue summarization …