A Study of Various Text Augmentation Techniques for Relation Classification in Free Text

Praveen Kumar Badimala Giridhara, Chinmaya Mishra, Reddy Kumar Modam Venkataramana, Syed Saqib Bukhari, Andreas Dengel

In: The 8th International Conference on Pattern Recognition Applications and Methods. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2019) February 19-21 Prague Czech Republic Insticc 2019.


Data augmentation techniques have been widely used in visual recognition tasks as it is easy to generate newdata by simple and straight forward image transformations. However, when it comes to text data augmen-tations, it is difficult to find appropriate transformation techniques which also preserve the contextual andgrammatical structure of language texts. In this paper, we explore various text data augmentation techniquesin text space and word embedding space. We study the effect of various augmented datasets on the efficiencyof different deep learning models for relation classification in text.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence