Image and Text: Fighting the Same Battle? Super-resolution Learning for Imbalanced Text Classification - Méthodes et Ingénierie des Langues, des Ontologies et du Discours
Communication Dans Un Congrès Année : 2023

Image and Text: Fighting the Same Battle? Super-resolution Learning for Imbalanced Text Classification

Résumé

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.
Fichier principal
Vignette du fichier
2023.findings-emnlp.718.pdf (550.71 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
licence
Domaine public

Dates et versions

hal-04347311 , version 1 (19-12-2023)

Licence

Domaine public

Identifiants

Citer

Romain Meunier, Farah Benamara, Véronique Moriceau, Patricia Stolf. Image and Text: Fighting the Same Battle? Super-resolution Learning for Imbalanced Text Classification. Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Dec 2023, Singapour, Singapore. pp.10707-10720, ⟨10.18653/v1/2023.findings-emnlp.718⟩. ⟨hal-04347311⟩
503 Consultations
112 Téléchargements

Altmetric

Partager

More