Mixup
Related Papers
Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks
AbstractMixup is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel …...
Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup
AbstractMixup is a recent regularizer for current deep classification networks. Through training a neural network on convex combinations of pairs of examples and their labels, it imposes locally linear constraints …...
BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch
Usually, we train a neural system on a se- quence of mini-batches of labeled instances. Each mini-batch is composed of k samples, and each sample will learn a representation vector. …...
Learning with Different Amounts of Annotation: From Zero to Many Labels
AbstractTraining NLP systems typically assumes access to annotated data that has a single human label per example. Given imperfect labeling from annotators and inherent ambiguity of language, we hypothesize that …...
Manifold Adversarial Augmentation for Neural Machine Translation
Improving the robustness of neural machine translation models on variations of input sen- tences is an active area of research. In this paper, we propose a simple data augmenta- tion …...
A Data Cartography based MixUp for Pre-trained Language Models
AbstractMixUp is a data augmentation strategy where additional samples are generated during training by combining random pairs of training samples and their labels. However, selecting random pairs is not potentially …...
DropMix: A Textual Data Augmentation Combining Dropout with Mixup
AbstractOverfitting is a notorious problem when there is insufficient data to train deep neural networks in machine learning tasks. Data augmentation regularization methods such as Dropout, Mixup, and their enhanced …...
Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition
AbstractNamed Entity Recognition (NER) systems often demonstrate great performance on in-distribution data, but perform poorly on examples drawn from a shifted distribution. One way to evaluate the generalization ability of …...
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency
AbstractA well-calibrated neural model produces confidence (probability outputs) closely approximated by the expected accuracy. While prior studies have shown that mixup training as a data augmentation technique can improve model …...
Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting
AbstractSelf-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup are two feasible heterogeneous self-augmentation techniques for NER that …...
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
AbstractTranslation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2) to …...
TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding
AbstractData augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, …...