We study the effect of different approaches to text augmentation. To do this we use three 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 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.
Reference:
Marivate, V. & Sefara, T.J. 2020. Improving short text classification through global augmentation methods. In International Cross-Domain Conference for Machine Learning and Knowledge Extraction. Springer, Cham, pp. 385-399
Marivate, V., & Sefara, T. J. (2020). Improving short text classification through global augmentation methods., Workflow;23683 http://hdl.handle.net/10204/11579
Marivate, V, and Tshephisho J Sefara. "Improving short text classification through global augmentation methods" In WORKFLOW;23683, n.p.: n.p. 2020. http://hdl.handle.net/10204/11579.
Marivate V, Sefara TJ. Improving short text classification through global augmentation methods.. Workflow;23683. [place unknown]: [publisher unknown]; 2020. [cited yyyy month dd]. http://hdl.handle.net/10204/11579.
Copyright: 2020 Springer. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website. The definitive version of the work is published in Holzinger A., Kieseberg P., Tjoa A., Weippl E. (eds) Machine Learning and Knowledge Extraction. CD-MAKE 2020. Lecture Notes in Computer Science, vol 12279. Springer, Cham. https://doi.org/10.1007/978-3-030-57321-8_21