Day-to-day, I’m working in a DevOps role to maintain a large-scale private cloud. I love computers and providing a platform for others to be more productive. I’m proficient in English, Indonesian, and Japanese, and I gladly put myself in a position where I can maximize this advantage.
Domain of interests:
– Storage, Server, and Virtualization layer in the infrastructure stack
– Consumer and Enterprise computer hardware
– Home lab and self-hosting
– Algorithms
– Linguistic: Code-switching (The act of mixing multiple languages in one sentence)
Various methods have been proposed to generate code-switched texts. Many of these involve training neural networks and, in turn, require some (albeit small) amounts of code-switched texts or parallel corpora to train the model itself. In this paper, we propose a method to convert monolingual text into a bilingual code-switched sentence using a dependency parser and machine translator. We leverage the characteristics of the dependency tree to identify the switching point and then pass it to machine translation to generate the code-switched sentence. We then surveyed multilingual people of respective language pairs to review the generated sentences and categorize the result. We found that our method is capable of generating natural code-switched text for various language pairs with the same algorithm. Our method does not require training and thus does not require training data. Our implementation of the model uses off-the-shelf components. The implementation is also built with the possibility of using purpose-built components and rapid deployability in mind.