Re-train or train from scratch? Comparing pre-training strategies of BERT in the medical domain

International audienceBERT models used in specialized domains all seem to be the result of a simple strategy: initializing with the original BERT and then resuming pre-training on a specialized corpus. This method yields rather good performance (e.g. BioBERT (Lee et al., 2020), SciBERT (Beltagy et al., 2019), BlueBERT (Peng et al., 2019)). However, it seems reasonable to think that training directly on a specialized corpus, using a specialized vocabulary, could result in more tailored embeddings and thus help performance. To test this hypothesis, we train BERT models from scratch using many configurations involving general and medical corpora. Based on evaluations using four different tasks, we find that the initial corpus only has a weak influence on the performance of BERT models when these are further pre-trained on a medical corpus