Portuguese Native Language Identification

摘要

This study presents the first Native Language Identification (NLI) study for L2 Portuguese. We used a sub-set of the NLI-PT dataset, containing texts written by speakers of five different native languages: Chinese, English, German, Italian, and Spanish. We explore the linguistic annotations available in NLI-PT to extract a range of (morpho-)syntactic features and apply NLI classification methods to predict the native language of the authors. The best results were obtained using an ensemble combination of the features, achieving 54.1% accuracy.