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

Abstract

Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Schu tze (2020) recently showed that these models struggle to under- stand rare words. For static word embeddings, this problem has been addressed by separately learning representations for rare words. In this work, we transfer this idea to pretrained language models: We introduce BERTRAM, a powerful architecture based on BERT that is capable of inferring high-quality embeddings for rare words that are suitable as input rep- resentations for deep language models. This is achieved by enabling the surface form and con- texts of a word to interact with each other in a deep architecture. Integrating BERTRAM into BERT leads to large performance increases due to improved representations of rare and medium frequency words on both a rare word probing task and three downstream tasks.