BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance

BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance Timo Schick author Hinrich Schütze author 2020-07 text Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Dan Jurafsky editor Joyce Chai editor Natalie Schluter editor Joel Tetreault editor Association for Computational Linguistics Online conference publication schick-schutze-2020-bertram 10.18653/v1/2020.acl-main.368 https://aclanthology.org/2020.acl-main.368/ 2020-07 3996 4007