This paper describes a methodology for syntactic knowledge transfer between high-resource languages to extremely low-resource languages. The methodology consists in leveraging multilingual BERT self-attention model pretrained on large datasets to develop a multilin
We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly
Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, ye
In cross-lingual dependency annotation projection, information is often lost during transfer because
Pretrained multilingual language models have become a common tool in transferring NLP capabilities t
Neural dependency parsing has achieved remarkable performance for many domains and languages. The bo