%0 Conference Proceedings
%T Improving Short Text Classification Through Global Augmentation Methods
%+ University of Pretoria [South Africa]
%+ Council for Scientific and Industrial Research [South Africa] (CSRI)
%+ Council for Scientific and Industrial Research [Pretoria] (CSIR)
%A Marivate, Vukosi
%A Sefara, Tshephisho
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE)
%C Dublin, Ireland
%Y Andreas Holzinger
%Y Peter Kieseberg
%Y A Min Tjoa
%Y Edgar Weippl
%I Springer International Publishing
%3 Machine Learning and Knowledge Extraction
%V LNCS-12279
%P 385-399
%8 2020-08-25
%D 2020
%R 10.1007/978-3-030-57321-8_21
%K Natural Language Processing
%K Data augmentation
%K Deep Neural Networks
%K Text classification
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X 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.
%G English
%Z TC 5
%Z TC 8
%Z TC 12
%Z WG 8.4
%Z WG 8.9
%Z WG 12.9
%2 https://inria.hal.science/hal-03414750/document
%2 https://inria.hal.science/hal-03414750/file/497121_1_En_21_Chapter.pdf
%L hal-03414750
%U https://inria.hal.science/hal-03414750
%~ SHS
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-TC8
%~ IFIP-WG8-4
%~ IFIP-WG8-9
%~ IFIP-CD-MAKE
%~ IFIP-WG12-9
%~ IFIP-LNCS-12279