IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages
This work addresses robustness in NLP for Indonesian code-mixed languages, which is an incremental domain-specific problem.
The paper tackles the problem of limited exploration of code-mixing in Indonesian NLP, focusing on robustness against diverse local languages like English, Sundanese, Javanese, and Malay, and introduces IndoRobusta as a framework for evaluation and improvement, with analysis showing that pre-training corpus bias affects models' handling of Indonesian-English code-mixing compared to other languages despite higher diversity.
Significant progress has been made on Indonesian NLP. Nevertheless, exploration of the code-mixing phenomenon in Indonesian is limited, despite many languages being frequently mixed with Indonesian in daily conversation. In this work, we explore code-mixing in Indonesian with four embedded languages, i.e., English, Sundanese, Javanese, and Malay; and introduce IndoRobusta, a framework to evaluate and improve the code-mixing robustness. Our analysis shows that the pre-training corpus bias affects the model's ability to better handle Indonesian-English code-mixing when compared to other local languages, despite having higher language diversity.