Authors:
Praveen Kumar Badimala Giridhara
1
;
Chinmaya Mishra
1
;
Reddy Kumar Modam Venkataramana
2
;
Syed Saqib Bukhari
3
and
Andreas Dengel
1
Affiliations:
1
Department of Computer Science, TU Kaiserslautern, Gottlieb-Daimler-Straße 47, Kaiserslautern, Germany, German Research Center for Artificial Intelligence (DFKI), Kaiserslautern and Germany
;
2
Department of Computer Science, TU Kaiserslautern, Gottlieb-Daimler-Straße 47, Kaiserslautern and Germany
;
3
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern and Germany
Keyword(s):
Relation Classification, Text Data Augmentation, Natural Language Processing, Investigative Study.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Feature Selection and Extraction
;
Knowledge Acquisition and Representation
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Natural Language Processing
;
Pattern Recognition
;
Symbolic Systems
;
Theory and Methods
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.