The BERT language model (LM) (Devlin et al., 2019) is surprisingly good at answering cloze-style questions about relational facts. Petroni et al. (2019) take this as evidence that BERT memorizes factual knowledge during pre-training. We take issue with this interpretation and argue that the performance of BERT is partly due to reasoning about (the surface form of) entity names, e.g., guessing that a person with an Italian-sounding name speaks Italian. More specifically, we show that BERT's precision drops dramatically when we filter certain easy-to-guess facts. As a remedy, we propose E-BERT, an extension of BERT that replaces entity mentions with symbolic entity embeddings. E-BERT outperforms both BERT and ERNIE (Zhang et al., 2019) on hard-to-guess queries. We take this as evidence that E-BERT is richer in factual knowledge, and we show two ways of ensembling BERT and E-BERT.
View on arXiv