State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
[HTML][HTML] Automated data processing and feature engineering for deep learning and big data applications: a survey
A Mumuni, F Mumuni - Journal of Information and Intelligence, 2024 - Elsevier
Modern approach to artificial intelligence (AI) aims to design algorithms that learn directly
from data. This approach has achieved impressive results and has contributed significantly …
from data. This approach has achieved impressive results and has contributed significantly …
A survey of automated data augmentation for image classification: Learning to compose, mix, and generate
Data augmentation is an effective way to improve the generalization of deep learning
models. However, the underlying augmentation methods mainly rely on handcrafted …
models. However, the underlying augmentation methods mainly rely on handcrafted …
A survey of automated data augmentation algorithms for deep learning-based image classification tasks
In recent years, one of the most popular techniques in the computer vision community has
been the deep learning technique. As a data-driven technique, deep model requires …
been the deep learning technique. As a data-driven technique, deep model requires …
GDA: Generative data augmentation techniques for relation extraction tasks
Relation extraction (RE) tasks show promising performance in extracting relations from two
entities mentioned in sentences, given sufficient annotations available during training. Such …
entities mentioned in sentences, given sufficient annotations available during training. Such …
Towards better detection of biased language with scarce, noisy, and biased annotations
Biased language is prevalent in today's online social media. To reduce the amount of online
biased language, one critical first step is to accurately detect such biased language, ideally …
biased language, one critical first step is to accurately detect such biased language, ideally …
Boosting text augmentation via hybrid instance filtering framework
Text augmentation is an effective technique for addressing the problem of insufficient data in
natural language processing. However, existing text augmentation methods tend to focus on …
natural language processing. However, existing text augmentation methods tend to focus on …
What makes better augmentation strategies? augment difficult but not too different
The practice of data augmentation has been extensively used to boost the performance of
deep neural networks for various NLP tasks. It is more effective when only a limited number …
deep neural networks for various NLP tasks. It is more effective when only a limited number …
Application of generative adversarial networks and Shapley algorithm based on easy data augmentation for imbalanced text data
JL Wu, S Huang - Applied Sciences, 2022 - mdpi.com
Imbalanced data constitute an extensively studied problem in the field of machine learning
classification because they result in poor training outcomes. Data augmentation is a method …
classification because they result in poor training outcomes. Data augmentation is a method …
AugCSE: Contrastive sentence embedding with diverse augmentations
Data augmentation techniques have been proven useful in many applications in NLP fields.
Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our …
Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our …