Exploring Data Augmentation Methods on Social Media Corpora

TL;DR

This paper evaluates various data augmentation techniques for NLP text classification on social media data, finding limited but promising improvements with certain methods and highlighting areas for future research.

Contribution

It systematically compares popular and novel data augmentation methods in NLP, including a new technique called Greyscaling, using social media datasets and BERT.

Findings

Synonym replacement shows some performance gains.

Greyscaling warrants further investigation.

Few-shot learning consistently improves results.

Abstract

Data augmentation has proven widely effective in computer vision. In Natural Language Processing (NLP) data augmentation remains an area of active research. There is no widely accepted augmentation technique that works well across tasks and model architectures. In this paper we explore data augmentation techniques in the context of text classification using two social media datasets. We explore popular varieties of data augmentation, starting with oversampling, Easy Data Augmentation (Wei and Zou, 2019) and Back-Translation (Sennrich et al., 2015). We also consider Greyscaling, a relatively unexplored data augmentation technique that seeks to mitigate the intensity of adjectives in examples. Finally, we consider a few-shot learning approach: Pattern-Exploiting Training (PET) (Schick et al., 2020). For the experiments we use a BERT transformer architecture. Results show that augmentation techniques provide only minimal and inconsistent improvements. Synonym replacement provided evidence of some performance improvement and adjective scales with Grayscaling is an area where further exploration would be valuable. Few-shot learning experiments show consistent improvement over supervised training, and seem very promising when classes are easily separable but further exploration would be valuable.