Cross-corpus Native Language Identification via Statistical Embedding

AbstractIn this paper, we approach the task of native language identification in a realistic cross-corpus scenario where a model is trained with available data and has to predict the native language from data of a different corpus. The motivation behind this study is to investigate native language identification in the Australian academic scenario where a majority of students come from China, Indonesia, and Arabic-speaking nations. We have proposed a statistical embedding representation reporting a significant improvement over common single-layer approaches of the state of the art, identifying Chinese, Arabic, and Indonesian in a cross-corpus scenario. The proposed approach was shown to be competitive even when the data is scarce and imbalanced.