Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
This addresses data scarcity for code-switching in NLP, which is domain-specific and speaker-dependent, though the method is incremental as it builds on existing GAN techniques.
The paper tackles the problem of insufficient data for code-switching tasks by proposing an unsupervised method using generative adversarial networks to generate intra-sentential code-switching sentences from monolingual data, resulting in improved performance for code-switching language models on two corpora.
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.