Massively multilingual language models (mPLMs) such as mBERT (Devlin et al., 2019) and XLM-R (Conneau et al., 2020) have become the driving force for a variety of applications in multilingual NLP (Pon
The Cross-lingual Natural Language Inference (XNLI) corpus is a crowd-sourced collection of 5,000 test and 2,500 dev pairs for the MultiNLI corpus. The pairs are annotated with textual entailment and
