Uncertainty in natural language processing: Sources, quantification, and applications

M Hu, Z Zhang, S Zhao, M Huang, B Wu - arxiv preprint arxiv:2306.04459, 2023‏ - arxiv.org
As a main field of artificial intelligence, natural language processing (NLP) has achieved
remarkable success via deep neural networks. Plenty of NLP tasks have been addressed in …

A survey of active learning for natural language processing

Z Zhang, E Strubell, E Hovy - arxiv preprint arxiv:2210.10109, 2022‏ - arxiv.org
In this work, we provide a survey of active learning (AL) for its applications in natural
language processing (NLP). In addition to a fine-grained categorization of query strategies …

Active learning by acquiring contrastive examples

K Margatina, G Vernikos, L Barrault… - arxiv preprint arxiv …, 2021‏ - arxiv.org
Common acquisition functions for active learning use either uncertainty or diversity
sampling, aiming to select difficult and diverse data points from the pool of unlabeled data …

Hyperspectral image classification with convolutional neural network and active learning

X Cao, J Yao, Z Xu, D Meng - IEEE Transactions on Geoscience …, 2020‏ - ieeexplore.ieee.org
Deep neural network has been extensively applied to hyperspectral image (HSI)
classification recently. However, its success is greatly attributed to numerous labeled …

Cold-start active learning through self-supervised language modeling

M Yuan, HT Lin, J Boyd-Graber - arxiv preprint arxiv:2010.09535, 2020‏ - arxiv.org
Active learning strives to reduce annotation costs by choosing the most critical examples to
label. Typically, the active learning strategy is contingent on the classification model. For …

[HTML][HTML] A review of hybrid approaches for quantitative assessment of crop traits using optical remote sensing: research trends and future directions

A Abdelbaki, T Udelhoven - Remote Sensing, 2022‏ - mdpi.com
Remote sensing technology allows to provide information about biochemical and
biophysical crop traits and monitor their spatiotemporal dynamics of agriculture ecosystems …

Better with less: A data-active perspective on pre-training graph neural networks

J Xu, R Huang, X Jiang, Y Cao… - Advances in neural …, 2023‏ - proceedings.neurips.cc
Pre-training on graph neural networks (GNNs) aims to learn transferable knowledge for
downstream tasks with unlabeled data, and it has recently become an active research area …

Active discriminative text representation learning

Y Zhang, M Lease, B Wallace - Proceedings of the AAAI conference on …, 2017‏ - ojs.aaai.org
We propose a new active learning (AL) method for text classification with convolutional
neural networks (CNNs). In AL, one selects the instances to be manually labeled with the …

Measuring data

M Mitchell, AS Luccioni, N Lambert, M Gerchick… - arxiv preprint arxiv …, 2022‏ - arxiv.org
We identify the task of measuring data to quantitatively characterize the composition of
machine learning data and datasets. Similar to an object's height, width, and volume, data …

Detection is better than cure: A cloud incidents perspective

V Ganatra, A Parayil, S Ghosh, Y Kang, M Ma… - Proceedings of the 31st …, 2023‏ - dl.acm.org
Cloud providers use automated watchdogs or monitors to continuously observe service
availability and to proactively report incidents when system performance degrades. Improper …