Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling


KESGİN H. T., AMASYALI M. F.

2nd International Conference on Advanced Engineering, Technology and Applications, ICAETA 2023, İstanbul, Turkey, 10 - 11 March 2023, vol.1983 CCIS, pp.450-463 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 1983 CCIS
  • Doi Number: 10.1007/978-3-031-50920-9_35
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.450-463
  • Keywords: data augmentation, language modeling, mask filling, text augmentation
  • Yıldız Technical University Affiliated: Yes

Abstract

Data augmentation is an effective technique for improving the performance of machine learning models. However, it has not been explored as extensively in natural language processing (NLP) as it has in computer vision. In this paper, we propose a novel text augmentation method that leverages the Fill-Mask feature of the transformer-based BERT model. Our method involves iteratively masking words in a sentence and replacing them with language model predictions. We have tested our proposed method on various NLP tasks and found it to be effective in many cases. Our results are presented along with a comparison to existing augmentation methods. Experimental results show that our proposed method significantly improves performance, especially on topic classification datasets.