Related papers: Enhancing Automated Essay Scoring with Three Techn…
Efficient text classification is essential for handling the increasing volume of academic publications. This study explores the use of pre-trained language models (PLMs), including BERT, SciBERT, BioBERT, and BlueBERT, fine-tuned on the Web…
While there are novel point cloud semantic segmentation schemes that continuously surpass state-of-the-art results, the success of learning an effective model usually rely on the availability of abundant labeled data. However, data…
While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of…
Improving performance in multiple domains is a challenging task, and often requires significant amounts of data to train and test models. Active learning techniques provide a promising solution by enabling models to select the most…
Self-supervised learning systems have gained significant attention in recent years by leveraging clustering-based pseudo-labels to provide supervision without the need for human annotations. However, the noise in these pseudo-labels caused…
The implementation of teaching interventions in learning needs has received considerable attention, as the provision of the same educational conditions to all students, is pedagogically ineffective. In contrast, more effectively considered…
We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…
In this paper, we present a semi-supervised training technique using pseudo-labeling for end-to-end neural diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, especially in…
Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement…
The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the…
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a…
Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test…
Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e.,\ compute clients) are idle much of the time, waiting for the next generation…
Entity Resolution (ER) is a critical task for data integration, yet state-of-the-art supervised deep learning models remain impractical for many real-world applications due to their need for massive, expensive-to-obtain labeled datasets.…
To improve deep-learning performance in low-resource settings, many researchers have redesigned model architectures or applied additional data (e.g., external resources, unlabeled samples). However, there have been relatively few…
In this paper, we propose a new Self-Supervised Learning (SSL) algorithm called data2vec-aqc, for speech representation learning from unlabeled speech data. Our goal is to improve SSL for speech in domains where both unlabeled and labeled…
This paper presents an approach to improve text embedding models through contrastive fine-tuning on small datasets augmented with expert scores. It focuses on enhancing semantic textual similarity tasks and addressing text retrieval…
Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the model has never been explicitly trained to identify. However,…
State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…
Machine learning methods based on AdaBoost have been widely applied to various classification problems across many mission-critical applications including healthcare, law and finance. However, there is a growing concern about the unfairness…