Code-Switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation

Ching-Ting Chang, Shun-Po Chuang, Hung-Yi Lee


Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-dependent and domain-related, so completely explaining the phenomenon by linguistic rules is challenging. Compared to most monolingual tasks, insufficient data is an issue for code-switching. To mitigate the issue without expensive human annotation, we proposed an unsupervised method for code-switching data augmentation. By utilizing a generative adversarial network, we can generate intra-sentential code-switching sentences from monolingual sentences. We applied the proposed method on two corpora, and the result shows that the generated code-switching sentences improve the performance of code-switching language models.


 DOI: 10.21437/Interspeech.2019-3214

Cite as: Chang, C., Chuang, S., Lee, H. (2019) Code-Switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation. Proc. Interspeech 2019, 554-558, DOI: 10.21437/Interspeech.2019-3214.


@inproceedings{Chang2019,
  author={Ching-Ting Chang and Shun-Po Chuang and Hung-Yi Lee},
  title={{Code-Switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={554--558},
  doi={10.21437/Interspeech.2019-3214},
  url={http://dx.doi.org/10.21437/Interspeech.2019-3214}
}