Related papers: Towards Integration of Statistical Hypothesis Test…

Hypothesis testing is a statistical inference approach used to determine whether data supports a specific hypothesis. An important type is the two-sample test, which evaluates whether two sets of data points are from identical…

Deep learning methods have proved highly effective for classification and image recognition problems. In this paper, we ask whether this success can be transferred to hypothesis testing: if a neural network can distinguish, for example, an…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Text classification, a core component of task-oriented dialogue systems, attracts continuous research from both the research and industry community, and has resulted in tremendous progress. However, existing method does not consider the use…

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…

Social scientists often classify text documents to use the resulting labels as an outcome or a predictor in empirical research. Automated text classification has become a standard tool, since it requires less human coding. However, scholars…

Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled…

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels…

Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label…

In supervised learning, automatically assessing the quality of the labels before any learning takes place remains an open research question. In certain particular cases, hypothesis testing procedures have been proposed to assess whether a…

With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…

Although deep learning models perform remarkably well across a range of tasks such as language translation and object recognition, it remains unclear what high-level logic, if any, they follow. Understanding this logic may lead to more…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Label smoothing is a widely used technique in various domains, such as text classification, image classification and speech recognition, known for effectively combating model overfitting. However, there is little fine-grained analysis on…

This study addresses the challenges of multi-label text classification. The difficulties arise from imbalanced data sets, varied text lengths, and numerous subjective feature labels. Existing solutions include traditional machine learning…

In multi-label classification, the main focus has been to develop ways of learning the underlying dependencies between labels, and to take advantage of this at classification time. Developing better feature-space representations has been…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Recent advancements in semi-supervised deep learning have introduced effective strategies for leveraging both labeled and unlabeled data to improve classification performance. This work proposes a semi-supervised framework that utilizes a…

Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…

Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is…