Tweeted By @seb_ruder
New paper with @mattthemathman & @nlpnoah on adapting pretrained representations: We compare feature extraction & fine-tuning with ELMo and BERT and try to give several guidelines for adapting pretrained representations in practice. https://t.co/yXcoLk6MkG pic.twitter.com/na3pu8UpCR
— Sebastian Ruder (@seb_ruder) March 16, 2019