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

Code

• github.com/ChingtingC/Code-Switching-Sentence-Generation-by-GAN
  none★ 0
• github.com/ChingtingC/Code-switching-Sentence-Generation-by-Generative-Adversarial-Networks-and-its-Application-to-Data-Au
  none★ 0

Abstract

Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-depend 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 proposed method on two corpora, and the result shows that the generated code-switching sentences improve the performance of code-switching language models.

Tasks

Reproductions