Lexical Data Augmentation for Text Classification in Deep Learning

Rong Xiang, Emmanuele Chersoni, Yunfei Long, Qin Lu, Chu-Ren Huang

Abstract

This paper presents our work on using part-of-speech focused lexical substitution for data augmentation (PLSDA) to enhance the prediction capabilities and the performance of deep learning models. This paper explains how PLSDA uses part-of-speech information to identify words and make use of different augmentation strategies to find semantically related substitutions to generate new instances for training. Evaluations of PLSDA is conducted on a variety of datasets across different text classification tasks. When PLSDA is applied to four deep learning models, results show that classifiers trained with PLSDA achieve 1.3% accuracy improvement on average.
BibTeX
@inproceedings{xiang2020lexical,
  author = {Rong Xiang and Emmanuele Chersoni and Yunfei Long and Qin Lu and Chu-Ren Huang},
  title = {{Lexical Data Augmentation for Text Classification in Deep Learning}},
  booktitle = {Canadian ai},
  year = {2020},
  doi = {10.1007/978-3-030-47358-7\_53},
}

Loading related content...

Figure