Related papers: Embeddings of Label Components for Sequence Labeli…

Multi-label classification (MLC) studies the problem where each instance is associated with multiple relevant labels, which leads to the exponential growth of output space. MLC encourages a popular framework named label compression (LC) for…

Multi-label classification is a type of supervised machine learning that can simultaneously assign multiple labels to an instance. To solve this task, some methods divide the original problem into several sub-problems (local approach),…

Tabular data learning has extensive applications in deep learning but its existing embedding techniques are limited in numerical and categorical features such as the inability to capture complex relationships and engineering. This paper…

Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time…

Entities are essential elements of natural language. In this paper, we present methods for learning multi-level representations of entities on three complementary levels: character (character patterns in entity names extracted, e.g., by…

We consider the problem of multi-label classification where the labels lie in a hierarchy. However, unlike most existing works in hierarchical multi-label classification, we do not assume that the label-hierarchy is known. Encouraged by the…

The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expensive. Active learning is a research area that addresses the…

Technological and computational advances continuously drive forward the broad field of deep learning. In recent years, the derivation of quantities describing theuncertainty in the prediction - which naturally accompanies the modeling…

Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generalizable and fast method…

Representing a true label as a one-hot vector is a common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instances and labels, as labels are often not…

A key obstacle in automated analytics and meta-learning is the inability to recognize when different datasets contain measurements of the same variable. Because provided attribute labels are often uninformative in practice, this task may be…

Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured…

Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component-enhanced Chinese…

This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected attributes, such as age, gender, or skin tone, can cause…

Machine learning-based multi-label medical text classifications can be used to enhance the understanding of the human body and aid the need for patient care. We present a broad study on clinical natural language processing techniques to…

Entity recognition is a fundamental task in understanding document images. Traditional sequence labeling frameworks treat the entity types as class IDs and rely on extensive data and high-quality annotations to learn semantics which are…

This paper presents a challenging computer vision task, namely the detection of generic components on a PCB, and a novel set of deep-learning methods that are able to jointly leverage the appearance of individual components and the…

We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we propose and evaluate several novel models consisting of (1) an…

In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures…

To advance the development of science and technology, research proposals are submitted to open-court competitive programs developed by government agencies (e.g., NSF). Proposal classification is one of the most important tasks to achieve…