Image and Text: Fighting the same Battle? Super Resolution Learning for Imbalanced Text Classification

Romain Meunier, Benamara Farah, Véronique Moriceau, Patricia Stolf

Submission Type: Regular Long Paper

Submission Track: Efficient Methods for NLP

Submission Track 2: NLP Applications

Keywords: Data Augmentation, Social media, Crisis management

Abstract: In this paper, we propose SRL4NLP, a new approach for data augmentation by drawing an analogy between image and text processing: Super-resolution learning. This method is based on using high-resolution images to overcome the problem of low resolution images. While this technique is a common usage in image processing when images have a low resolution or are too noisy, it has never been used in NLP. We therefore propose the first adaptation of this method for text classification and evaluate its effectiveness on urgency detection from tweets posted in crisis situations, a very challenging task where messages are scarce and highly imbalanced. We show that this strategy is efficient when compared to competitive state-of-the-art data augmentation techniques on several benchmarks datasets in two languages.

Submission Number: 3279