no code implementations • ACL (RepL4NLP) 2021 • Nicolai Pogrebnyakov, Shohreh Shaghaghian
Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain.
no code implementations • 10 Feb 2021 • Shohreh Shaghaghian, Luna, Feng, Borna Jafarpour, Nicolai Pogrebnyakov
Inspired by the inductive transfer learning on computer vision, many efforts have been made to train contextualized language models that boost the performance of natural language processing tasks.