Deep learning is an effective method for extracting the underlying information in text.
However, it performs better on closed datasets and is less effective in real-world scenarios …

Background and objective Cancer grading in pathology image analysis is a major task due
to its importance in patient care, treatment, and management. The recent developments in …

Large amounts of data are often categorized using different systems. In such cases, few-shot
and unsupervised text classification are the two main approaches for dynamically classifying …

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 …

MeSH (Medical Subject Headings) is a large thesaurus created by the National Library of
Medicine and used for fine-grained indexing of publications in the biomedical domain. In the …

Biomedical entity linking task is the task of mapping mention (s) that occur in a particular
textual context to a unique concept or entity in a knowledge base, eg, the Unified Medical …

As few-shot relation classification requires less data to train the neural network models, high
costs related to data collection and labeling are eliminated. Compared with the traditional …

Spatial optimization is often overlooked in many computer vision tasks. Filters should be
able to recognize the features of an object regardless of where it is in the image. Similarity …

An overview of deep metric learning methods is presented. Although they have appeared in
recent years, these methods were compared only with their predecessors, with neural …

Current state-of-the-art approaches to text classification typically leverage BERT-style
Transformer models with a softmax classifier, jointly fine-tuned to predict class labels of a …