Sibylvariant Transformations for Robust Text Classification
The vast majority of text transformation techniques in NLP are inherently limited in their ability to expand input space coverage due to an implicit constraint to preserve the original class label. In this work, we propose the notion of sibylvariance (SIB) to describe the broader set of transforms that relax the label-preserving constraint, knowably vary the expected class, and lead to significantly more diverse input distributions. We offer a unified framework to organize all data transformations, including two types of SIB: (1) Transmutations convert one discrete kind into another, (2) Mixture Mutations blend two or more classes together. To explore the role of sibylvariance within NLP, we implemented 41 text transformations, including several novel techniques like Concept2Sentence and SentMix. Sibylvariance also enables a unique form of adaptive training that generates new input mixtures for the most confused class pairs, challenging the learner to differentiate with greater nuance. Our experiments on six benchmark datasets strongly support the efficacy of sibylvariance for generalization performance, defect detection, and adversarial robustness.
Code (1)
Tasks
Adversarial RobustnessDefect DetectionGeneral ClassificationText ClassificationSimilar Papers 제목 키워드 기반
Conformal Transformation of Kernels: A Geometric Perspective on Text Classification
In this article we investigate the effects of conformal transformations on kernel functions used in Support Vector Machines. Our focus lies in the task of text document categorization, which involves assigning each docum…
Binary Classificationtext-classificationText ClassificationTransformNet: Self-supervised representation learning through predicting geometric transformations
Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited …
Data Augmentationimage-classificationImage ClassificationRepresentation LearningCastor: Competing shapelets for fast and accurate time series classification
Shapelets are discriminative subsequences, originally embedded in shapelet-based decision trees but have since been extended to shapelet-based transformations. We propose Castor, a simple, efficient, and accurate time se…
Time SeriesTime Series ClassificationOn the Generalization Effects of Linear Transformations in Data Augmentation
Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. Yet, there is little rigorous understanding of why and how various augmentations work. In this…
Data Augmentationtext-classificationText ClassificationDistribution Estimation to Automate Transformation Policies for Self-Supervision
In recent visual self-supervision works, an imitated classification objective, called pretext task, is established by assigning labels to transformed or augmented input images. The goal of pretext can be predicting what …
Generative Adversarial NetworkSelf-Supervised Learning