Improving short text classification through global augmentation methods

By Vukosi Marivate, Tshephisho Joseph Sefara. 2019

111 citations recorded by the source corpus.

We study the effect of different approaches to text augmentation. To do this we use 3 datasets that include social media and formal text in the form of news articles. Our goal is to provide insights for practitioners and researchers on making choices for augmentation for classification use cases. We observe that Word2vec-based augmentation is a viable option when one does not have access to a formal synonym model (like WordNet-based augmentation). The use of \emph{mixup} further improves performance of all text based augmentations and reduces the effects of overfitting on a tested deep learning model. Round-trip translation with a translation service proves to be harder to use due to cost and as such is less accessible for both normal and low resource use-cases.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Do Not Have Enough Data? Deep Learning to the Rescue! (2019, neutral): “These methods were analyzed in (Marivate and Sefara 2019).”
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation (2021, background): “This perturbation randomly swaps two adjacent characters in a sentence or a paragraph with a default probability (Zhang et al., 2019a).”
A Survey on Data Augmentation for Text Classification (2021, unknown): “Marivate and Sefara [64] state that they use mixup on representations of bag of word models, TF.IDF models, word embeddings, and language models.”