MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer by Jonas Pfeiffer, Sebastian Ruder, Ivan Vulic, Iryna Gurevych
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer

Jonas Pfeiffer, Sebastian Ruder, Ivan Vulic, Iryna Gurevych

MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer

Jonas Pfeiffer, Sebastian Ruder, Ivan Vulic, Iryna Gurevych

20 pages first pub 2020 (editions) not a book user-added

nonfiction computer science science technology

Description

AbstractThe main goal behind state-of-the-art pretrained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot crosslingual transfer. However,...

Read more

Community Reviews

Loading...

Content Warnings

Loading...