Sibylvariant Transformations for Robust Text Classification. (arXiv:2205.05137v1 [cs.CL])

Web: http://arxiv.org/abs/2205.05137

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 …

arxiv classification text text classification