Text is an Image: Augmentation via Embedding Mixing

K. Zhao, V. Lialin, A. Rumshisky., MIT PRIMES, 2020

Paper link

Data augmentation techniques are essential for computer vision, yielding signif- icant accuracy improvements with little engineering costs. However, data aug- mentation for text has always been tricky. Synonym replacement techniques re- quire a good thesaurus and domain-specific rules for synonym selection from the synset, while backtranslation techniques are computationally expensive and re- quire a good translation model for the language in interest. In this paper, we present simple text augmentation techniques on the embed- dings level, inspired by mixing-based image augmentations. These techniques are language-agnostic and require little to no hyperparameter tuning. We evaluate the augmentation techniques on IMDB and GLUE tasks, and the results show that the augmentations significantly improve the score of the RoBERTa model.


    title={Text is an Image: Augmentation via Embedding Mixing},
    author={Kevin Zhao and Vladislav Lialin and Anna Rumshisky},