Related papers: Diversifying Dialog Generation via Adaptive Label …

Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and…

Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-density regions of the training distribution, these models…

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

Recently, Visual Foundation Models (VFMs) have shown a remarkable generalization performance in 3D perception tasks. However, their effectiveness in large-scale outdoor datasets remains constrained by the scarcity of accurate supervision…

As one of the most exciting features of large language models (LLMs), in-context learning is a mixed blessing. While it allows users to fast-prototype a task solver with only a few training examples, the performance is generally sensitive…

Many sequence-to-sequence dialogue models tend to generate safe, uninformative responses. There have been various useful efforts on trying to eliminate them. However, these approaches either improve decoding algorithms during inference,…

Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus. Some methods are proposed to address the…

Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. This problem is often aggravated by discrepancies between…

In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set,…

In this paper, we propose a novel strategy for text-independent speaker identification system: Multi-Label Training (MLT). Instead of the commonly used one-to-one correspondence between the speech and the speaker label, we divide all the…

The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \emph{unlabelled} test sample. This sample may be…

Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods…

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

This paper presents a novel knowledge distillation method for dialogue sequence labeling. Dialogue sequence labeling is a supervised learning task that estimates labels for each utterance in the target dialogue document, and is useful for…

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data, spanning homophilic to heterophilic graphs, remains largely unexplored. We introduce…

Label smoothing is a regularization technique for neural networks. Normally neural models are trained to an output distribution that is a vector with a single 1 for the correct prediction, and 0 for all other elements. Label smoothing…

A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can end up being far from the clean training data and what is the…

When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from…

Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the…