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

Praveen Giridhara, Chinmaya Mishra, Reddy Venkataramana, Syed Bukhari, Andreas Dengel

2019

Abstract

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

Paper Citation

in Harvard Style

Giridhara P., Mishra C., Venkataramana R., Bukhari S. and Dengel A. (2019). A Study of Various Text Augmentation Techniques for Relation Classification in Free Text.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 360-367. DOI: 10.5220/0007311003600367

in Bibtex Style

@conference{icpram19,
author={Praveen Giridhara and Chinmaya Mishra and Reddy Venkataramana and Syed Bukhari and Andreas Dengel},
title={A Study of Various Text Augmentation Techniques for Relation Classification in Free Text},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={360-367},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007311003600367},
isbn={978-989-758-351-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Study of Various Text Augmentation Techniques for Relation Classification in Free Text
SN - 978-989-758-351-3
AU - Giridhara P.
AU - Mishra C.
AU - Venkataramana R.
AU - Bukhari S.
AU - Dengel A.
PY - 2019
SP - 360
EP - 367
DO - 10.5220/0007311003600367